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

    Neuronpedia

    INDEX
    Explanations

    dialogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     invari
    -0.09
    Invariant
    -0.09
     invariant
    -0.08
    _SMS
    -0.08
    _PROM
    -0.08
     discriminatory
    -0.08
     Каз
    -0.08
     подраз
    -0.08
    paar
    -0.08
     pencil
    -0.08
    POSITIVE LOGITS
     welcomed
    0.11
     apologized
    0.11
     greeted
    0.10
     apolog
    0.10
     greetings
    0.10
     traer
    0.10
    歉
    0.10
    Welcome
    0.09
     enthusiastic
    0.09
    welcome
    0.09
    Act Density 0.038%

    No Known Activations