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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fluid
    -0.07
    icio
    -0.07
    лася
    -0.07
     Ther
    -0.07
     collected
    -0.06
    WHO
    -0.06
    MMC
    -0.06
     Fluid
    -0.06
    categoria
    -0.06
    舞
    -0.06
    POSITIVE LOGITS
    .containsKey
    0.08
     广
    0.07
    入
    0.07
    (comb
    0.07
    包含
    0.07
    Reserved
    0.06
     parenthesis
    0.06
    _wrong
    0.06
     ست
    0.06
     TBranch
    0.06
    Act Density 0.001%

    No Known Activations