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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Sah
    -0.07
    BU
    -0.07
    bout
    -0.07
    78
    -0.07
     phúc
    -0.06
    -corner
    -0.06
     Backend
    -0.06
    LAB
    -0.06
    /X
    -0.06
    ‌المللی
    -0.06
    POSITIVE LOGITS
     the
    0.07
     піш
    0.07
     іде
    0.06
    .appcompat
    0.06
     �
    0.06
     ún
    0.06
     wrestling
    0.06
     unmistak
    0.06
                ↵↵
    0.06
     여성
    0.06
    Act Density 0.036%

    No Known Activations