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

    Neuronpedia

    INDEX
    Explanations

    structural and architectural information about buildings

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

    again

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    imp
    -0.40
     
    -0.39
     McCartney
    -0.39
    Root
    -0.38
     formal
    -0.38
    ections
    -0.38
    isierten
    -0.38
    APS
    -0.37
    ariat
    -0.37
    det
    -0.37
    POSITIVE LOGITS
    Again
    2.00
     Again
    1.96
     again
    1.89
    again
    1.88
    こちらも
    1.79
     opět
    1.53
     novamente
    1.53
     AGAIN
    1.52
     опять
    1.49
     nuevamente
    1.48
    Act Density 0.302%

    No Known Activations