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

    Neuronpedia

    INDEX
    Explanations

    suggestions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     المو
    -0.07
    ?):
    -0.06
    .fragment
    -0.06
    _Manager
    -0.06
     garbage
    -0.06
    larından
    -0.06
     trộn
    -0.06
     dildo
    -0.05
    ANS
    -0.05
     �
    -0.05
    POSITIVE LOGITS
     instituted
    0.07
    mac
    0.07
    164
    0.07
     ={↵
    0.06
    わたし
    0.06
     recommending
    0.06
     strengths
    0.06
     jedem
    0.06
    BM
    0.06
    843
    0.06
    Act Density 0.080%

    No Known Activations