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

    Neuronpedia

    INDEX
    Explanations

    document

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (factor
    -0.07
    Relation
    -0.07
     ()
    -0.07
    _CLI
    -0.07
    配
    -0.07
     arguably
    -0.06
    ."','".$
    -0.06
    ，同时
    -0.06
     Aaron
    -0.06
    เฟ
    -0.06
    POSITIVE LOGITS
     document
    0.07
    Seleccione
    0.07
     Outputs
    0.07
    objects
    0.06
     TLabel
    0.06
     documentation
    0.06
     Episode
    0.06
    _FIELD
    0.06
     Luther
    0.06
    uator
    0.06
    Act Density 0.006%

    No Known Activations