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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Zuk
    -0.07
     přitom
    -0.07
     coppia
    -0.06
    �
    -0.06
     banda
    -0.06
    vem
    -0.06
     busy
    -0.06
    930
    -0.06
     Ν
    -0.06
    라인
    -0.06
    POSITIVE LOGITS
    .',
    0.07
    OUCH
    0.07
     Національ
    0.06
    .Gravity
    0.06
     обрат
    0.06
     coalition
    0.06
     metabolic
    0.06
    imizer
    0.06
     readable
    0.06
    али
    0.06
    Act Density 0.004%

    No Known Activations