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

    Neuronpedia

    INDEX
    Explanations

    regulated

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    笃
    -0.07
    itize
    -0.07
     сох
    -0.07
    🥕
    -0.07
    Ә
    -0.07
    ɕ
    -0.07
    慌
    -0.07
    颏
    -0.07
    ڑ
    -0.07
    .ResponseWriter
    -0.07
    POSITIVE LOGITS
     Came
    0.07
    _inst
    0.07
    Nm
    0.07
     был
    0.06
    -square
    0.06
     interests
    0.06
    .member
    0.06
     coating
    0.06
     Fiat
    0.06
    World
    0.06
    Act Density 0.003%

    No Known Activations