Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    descriptions of agreement and stability in social or political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by verbs of perception/appearance

    np_acts-logits-general · gemini-2.0-flash

    everything seemed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     متحده
    -0.63
     bukan
    -0.58
    ValueStyle
    -0.58
     prefier
    -0.57
    ScopeManager
    -0.57
     instead
    -0.56
     rather
    -0.56
     onFailure
    -0.54
    difer
    -0.54
    akter
    -0.53
    POSITIVE LOGITS
     вроде
    0.92
     казалось
    0.91
     seemingly
    0.83
     promising
    0.81
     seeming
    0.79
     supposed
    0.79
     pourtant
    0.77
    好不容易
    0.76
     supposedly
    0.74
     touted
    0.74
    Act Density 0.342%

    No Known Activations