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

    Neuronpedia

    INDEX
    Explanations

    Book information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inclusive
    -0.07
    -webpack
    -0.07
    .rating
    -0.07
    ksiyon
    -0.07
    _Exception
    -0.07
    manage
    -0.06
    _domains
    -0.06
     newSize
    -0.06
    (cpu
    -0.06
    -categories
    -0.06
    POSITIVE LOGITS
     IDENT
    0.06
     Elim
    0.06
     immac
    0.06
    ="/">
    0.06
     backs
    0.06
    Ut
    0.06
    �
    0.06
    ันท
    0.06
    ()}}↵
    0.06
     Plaintiff
    0.05
    Act Density 0.007%

    No Known Activations