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

    Neuronpedia

    INDEX
    Explanations

    Reviews and descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     organizer
    -0.06
     Instructor
    -0.06
     代
    -0.06
    VERY
    -0.06
    urum
    -0.06
    nit
    -0.06
     ziy
    -0.06
    (selector
    -0.06
     tự
    -0.06
    IGNORE
    -0.06
    POSITIVE LOGITS
    HQ
    0.07
     Antib
    0.06
     HQ
    0.06
     "}\
    0.06
    ักษณ
    0.06
    getPosition
    0.06
    tridges
    0.06
    packageName
    0.06
    _ipv
    0.06
     Humans
    0.06
    Act Density 0.000%

    No Known Activations