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

    Neuronpedia

    INDEX
    Explanations

    new

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    burn
    -0.07
    iteration
    -0.06
    mint
    -0.06
    west
    -0.06
    /wp
    -0.06
    _related
    -0.06
    Editing
    -0.06
     vật
    -0.06
    amientos
    -0.06
    $core
    -0.06
    POSITIVE LOGITS
     financially
    0.07
     TED
    0.07
     exc
    0.07
    sealed
    0.07
    urchase
    0.07
    .expires
    0.06
     gaussian
    0.06
    %D
    0.06
     homer
    0.06
     확
    0.06
    Act Density 0.012%

    No Known Activations