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

    Neuronpedia

    INDEX
    Explanations

    debut

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Drv
    -0.08
     Pope
    -0.07
    subjects
    -0.07
    esda
    -0.06
     Governor
    -0.06
    .cleaned
    -0.06
     watering
    -0.06
     Carp
    -0.06
    .task
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    κυ
    0.07
     Range
    0.06
    √
    0.06
     anal
    0.06
    istingu
    0.06
     ACCEPT
    0.06
     scheduled
    0.06
     routine
    0.06
    计算
    0.06
    имо
    0.06
    Act Density 0.015%

    No Known Activations