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

    Neuronpedia

    INDEX
    Explanations

    rib

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    REM
    -0.07
    Phil
    -0.07
     overweight
    -0.07
    frauen
    -0.06
    GetProperty
    -0.06
     측
    -0.06
    isations
    -0.06
     Dep
    -0.06
    Ted
    -0.06
    HERE
    -0.06
    POSITIVE LOGITS
     genius
    0.07
    егод
    0.07
    ?:
    0.06
    도
    0.06
     UIStoryboardSegue
    0.06
     [][]
    0.06
    asString
    0.06
     σε
    0.06
    Composer
    0.06
    ð
    0.06
    Act Density 0.002%

    No Known Activations