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

    Neuronpedia

    INDEX
    Explanations

    code, documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .have
    -0.07
    二二
    -0.07
     jails
    -0.06
    RH
    -0.06
     nk
    -0.06
    asjon
    -0.06
     simulate
    -0.06
     Tournament
    -0.06
    *this
    -0.06
     knife
    -0.06
    POSITIVE LOGITS
     printers
    0.06
    specs
    0.06
    ered
    0.06
    district
    0.06
    (priv
    0.06
     Alta
    0.06
     elevated
    0.06
    phins
    0.06
     MIPS
    0.06
    律宾
    0.06
    Act Density 0.000%

    No Known Activations