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

    Neuronpedia

    INDEX
    Explanations

    Foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    %timeout
    -0.08
     JK
    -0.07
     teens
    -0.07
     Width
    -0.07
     triangles
    -0.07
     users
    -0.07
     durability
    -0.07
    锤
    -0.07
     Erica
    -0.07
     recognition
    -0.07
    POSITIVE LOGITS
    bij
    0.07
    وسط
    0.07
     נת
    0.07
    ホール
    0.07
    Federal
    0.07
    中超
    0.07
    这个地方
    0.07
    וצר
    0.07
    об
    0.07
    oultry
    0.07
    Act Density 0.012%

    No Known Activations