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

    Neuronpedia

    INDEX
    Explanations

    code/technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Razor
    -0.07
     manned
    -0.07
    Cette
    -0.06
     fileSize
    -0.06
    Typ
    -0.06
     LSU
    -0.06
    _imm
    -0.06
    [ip
    -0.06
     начала
    -0.06
    Blockly
    -0.06
    POSITIVE LOGITS
    _features
    0.07
    junction
    0.07
     '',
↵
    0.06
     eso
    0.06
    merchant
    0.06
     trabal
    0.06
     Elizabeth
    0.06
    .DataFrame
    0.06
    스템
    0.06
     amer
    0.06
    Act Density 0.014%

    No Known Activations