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

    Neuronpedia

    INDEX
    Explanations

    situations involving crime and legal issues

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

    Following prepositions or certain verbs

    np_acts-logits-general · gemini-2.0-flash

    adoptions, allegedly, Chinese, conversion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anything
    -0.65
    anything
    -0.65
    Anything
    -0.64
     broadest
    -0.63
    everything
    -0.62
     Wherever
    -0.61
     wherever
    -0.61
    anywhere
    -0.60
    大体
    -0.59
    Wherever
    -0.58
    POSITIVE LOGITS
     allegedly
    0.69
    principalColumn
    0.63
     Chinese
    0.61
    انجليز
    0.58
     his
    0.58
     supposedly
    0.57
     supposed
    0.57
    ètres
    0.56
    yns
    0.56
     drunken
    0.56
    Act Density 0.609%

    No Known Activations