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

    Neuronpedia

    INDEX
    Explanations

    .Runtime

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    makers
    -0.06
    (button
    -0.06
    显示
    -0.06
    _str
    -0.06
    ificantly
    -0.06
     film
    -0.06
    iate
    -0.06
     السلام
    -0.06
     Fiona
    -0.06
    228
    -0.06
    POSITIVE LOGITS
    orer
    0.07
    anship
    0.07
    theid
    0.07
    (CH
    0.07
     Peb
    0.06
     Squad
    0.06
    ũ
    0.06
     �
    0.06
     remotely
    0.06
    rganization
    0.06
    Act Density 0.001%

    No Known Activations