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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     joke
    -0.08
     defin
    -0.07
    営
    -0.07
     sixth
    -0.07
    есь
    -0.06
     AC
    -0.06
    ('');↵↵
    -0.06
     enlightened
    -0.06
    亡
    -0.06
    ک
    -0.06
    POSITIVE LOGITS
    ificant
    0.07
    .textLabel
    0.06
    **)
    0.06
    esser
    0.06
     AttributeSet
    0.06
    _triangle
    0.06
    astle
    0.06
    拿
    0.06
     Serialized
    0.06
    领域
    0.06
    Act Density 0.008%

    No Known Activations