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

    Neuronpedia

    INDEX
    Explanations

    animal release into the wild

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interiors
    -0.07
    约
    -0.07
    vider
    -0.06
    edith
    -0.06
    जर
    -0.06
    .embed
    -0.06
     طرف
    -0.06
    -blood
    -0.06
    ของร
    -0.06
    方
    -0.06
    POSITIVE LOGITS
    (val
    0.06
    ([[
    0.06
     servant
    0.06
     shrugged
    0.06
     ،
    0.06
    _make
    0.06
     ningún
    0.06
     gid
    0.06
     [[
    0.06
     göl
    0.06
    Act Density 0.010%

    No Known Activations