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

    Neuronpedia

    INDEX
    Explanations

    code completion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cycles
    -0.08
    Text
    -0.07
    Eval
    -0.07
     dictated
    -0.07
     apps
    -0.07
    แผ
    -0.07
     words
    -0.06
    acción
    -0.06
     --↵
    -0.06
     Reduction
    -0.06
    POSITIVE LOGITS
    _ROLE
    0.06
     солн
    0.06
     sellers
    0.06
     kims
    0.06
    اصل
    0.06
    彡
    0.06
     Львів
    0.06
     flowing
    0.06
     Lowe
    0.06
     Baghdad
    0.06
    Act Density 0.105%

    No Known Activations