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

    Neuronpedia

    INDEX
    Explanations

    .org

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (rb
    -0.06
    (mask
    -0.06
    Ascii
    -0.06
    .Con
    -0.06
     simult
    -0.06
    .INVALID
    -0.06
     tercer
    -0.06
    нка
    -0.06
     landed
    -0.06
    .finish
    -0.06
    POSITIVE LOGITS
    ho
    0.07
     هن
    0.07
     rebell
    0.06
    妖
    0.06
    остью
    0.06
    doing
    0.06
     milit
    0.06
     هنر
    0.06
     Tracks
    0.06
     �
    0.06
    Act Density 0.000%

    No Known Activations