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

    Neuronpedia

    INDEX
    Explanations

    Negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    esin
    -0.06
     volont
    -0.06
     comerc
    -0.06
    晶
    -0.06
    oğan
    -0.06
    (objects
    -0.06
    "]);
    -0.06
     whistle
    -0.06
     |--
    -0.06
    .JSONException
    -0.06
    POSITIVE LOGITS
     çek
    0.07
    �
    0.07
     Hindus
    0.06
    /cache
    0.06
     sentiment
    0.06
     trophy
    0.06
     Lub
    0.06
    Si
    0.06
     Pike
    0.06
     frac
    0.06
    Act Density 0.015%

    No Known Activations