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

    Neuronpedia

    INDEX
    Explanations

    trail

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DENIED
    -0.07
     �
    -0.07
     �
    -0.07
    ucch
    -0.06
     mang
    -0.06
     �
    -0.06
     yakın
    -0.06
    百
    -0.06
    -Day
    -0.06
     skeptic
    -0.06
    POSITIVE LOGITS
     ballistic
    0.06
    |↵
    0.06
    .network
    0.06
    Vectorizer
    0.06
    (rate
    0.06
    _RUNTIME
    0.06
     nur
    0.06
    relations
    0.06
    очные
    0.06
    >.
    0.06
    Act Density 0.000%

    No Known Activations