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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ←
    -0.07
     gradu
    -0.06
     �
    -0.06
     village
    -0.06
    Jesus
    -0.06
    SUB
    -0.06
    (@
    -0.06
     jaký
    -0.06
     warmly
    -0.06
    〔
    -0.06
    POSITIVE LOGITS
     microtime
    0.07
    vla
    0.07
     sensible
    0.06
    .course
    0.06
    ublish
    0.06
    _bank
    0.06
     kuchy
    0.06
    LOCKS
    0.06
     Jays
    0.06
    _po
    0.06
    Act Density 0.003%

    No Known Activations