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

    Neuronpedia

    INDEX
    Explanations

    discussions about actions and behaviors, particularly those that are done well or incorrectly

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

    doing things the wrong way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.57
    autaire
    -0.48
    rxjs
    -0.45
     squash
    -0.45
     jsPsych
    -0.45
    WebElementEntity
    -0.44
    dflare
    -0.44
     monster
    -0.43
    umsi
    -0.43
     BorderSide
    -0.43
    POSITIVE LOGITS
    évaluateur
    0.51
    SequentialGroup
    0.45
     MainAxisSize
    0.42
     Infórmanos
    0.40
     invokingState
    0.39
     préférence
    0.38
     avulla
    0.38
    lış
    0.37
     kerk
    0.36
    følgelig
    0.36
    Act Density 0.017%

    No Known Activations