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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "With
    -0.08
     Supporting
    -0.07
    憺
    -0.07
     ParameterDirection
    -0.07
     labelText
    -0.07
     Bison
    -0.07
    _atual
    -0.07
     Saves
    -0.07
    进货
    -0.07
     pointed
    -0.07
    POSITIVE LOGITS
    .TrimSpace
    0.09
    otics
    0.07
    伞
    0.07
    bat
    0.07
    ensa
    0.07
    _memory
    0.07
    embrance
    0.07
    所有的
    0.06
    odash
    0.06
    _NAMESPACE
    0.06
    Act Density 0.081%

    No Known Activations