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

    Neuronpedia

    INDEX
    Explanations

    Negation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    913
    -0.06
    uitka
    -0.06
     �
    -0.06
    sworth
    -0.06
    -co
    -0.06
    γι
    -0.06
     alerts
    -0.06
     plugs
    -0.06
     Kut
    -0.06
     Sandra
    -0.06
    POSITIVE LOGITS
     BOX
    0.07
     професси
    0.06
    (engine
    0.06
     rigorous
    0.06
    _UNDEFINED
    0.06
    infos
    0.06
    leine
    0.06
     wireType
    0.06
    ，此
    0.06
    usher
    0.06
    Act Density 0.062%

    No Known Activations