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

    Neuronpedia

    INDEX
    Explanations

    read

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gala
    -0.07
    cert
    -0.07
    .Lock
    -0.07
     免
    -0.06
    placement
    -0.06
     Explosion
    -0.06
     ballet
    -0.06
     cave
    -0.06
    sigmoid
    -0.06
    tyard
    -0.06
    POSITIVE LOGITS
    \D
    0.06
    ordum
    0.06
    (Runtime
    0.06
    ",↵↵
    0.06
    兴
    0.06
    '];?></
    0.06
     sideways
    0.06
    :y
    0.06
    =db
    0.06
    ');?></
    0.06
    Act Density 0.021%

    No Known Activations