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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oscill
    -0.07
    idir
    -0.07
    té
    -0.06
     vál
    -0.06
    !_
    -0.06
    /,
    -0.06
    -version
    -0.06
    -duration
    -0.06
    drs
    -0.06
     öden
    -0.06
    POSITIVE LOGITS
     Honey
    0.08
     Lane
    0.07
    Street
    0.06
    UNCTION
    0.06
     Hot
    0.06
     xử
    0.06
    UPPORT
    0.06
    Config
    0.06
     somew
    0.06
     Dublin
    0.06
    Act Density 0.000%

    No Known Activations