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

    Neuronpedia

    INDEX
    Explanations

    opinion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     precondition
    -0.07
    ког
    -0.07
    _PROXY
    -0.07
     skulle
    -0.07
     Validators
    -0.06
    qd
    -0.06
    Locale
    -0.06
     فرزند
    -0.06
    hq
    -0.06
    favor
    -0.06
    POSITIVE LOGITS
    inished
    0.06
    wick
    0.06
    gra
    0.06
    outing
    0.06
    Smoke
    0.06
     supreme
    0.06
    iously
    0.06
    employed
    0.06
    .Report
    0.06
    Blake
    0.06
    Act Density 0.001%

    No Known Activations