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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal experiences and sharing sentiments

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

    I am, I'm, I did

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.56
     zaczą
    -0.52
     empezaron
    -0.49
     comenzaron
    -0.47
     pernah
    -0.46
     anfangs
    -0.45
     inició
    -0.45
    unächst
    -0.44
     decidieron
    -0.43
    transQ
    -0.42
    POSITIVE LOGITS
     enjoyed
    0.63
    Enjoyed
    0.56
    Overall
    0.53
     overall
    0.50
     Overall
    0.50
     regrets
    0.50
     exhausted
    0.47
     vold
    0.45
    LayoutPanel
    0.44
    下次
    0.43
    Act Density 0.034%

    No Known Activations