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

    Neuronpedia

    INDEX
    Explanations

    should

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    WithType
    -0.07
    蝠
    -0.07
     chiếm
    -0.07
     Sno
    -0.07
    🇼
    -0.07
    𫚕
    -0.07
    only
    -0.07
     seeking
    -0.06
    ’ve
    -0.06
    POSITIVE LOGITS
    𝘂
    0.07
    ﻓ
    0.07
    jourd
    0.07
    odu
    0.07
     deut
    0.07
    (ht
    0.07
    outfile
    0.07
     rowCount
    0.07
    それを
    0.07
    干活
    0.07
    Act Density 0.001%

    No Known Activations