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

    Neuronpedia

    INDEX
    Explanations

    school/traffic issues

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    芝麻
    -0.07
    กรม
    -0.07
    -le
    -0.07
     Literal
    -0.07
    犊
    -0.07
     Mazda
    -0.07
    _COMMON
    -0.07
    $new
    -0.07
    在美国
    -0.06
    êu
    -0.06
    POSITIVE LOGITS
    ват
    0.07
    ሀ
    0.07
    significant
    0.07
    stats
    0.07
    рист
    0.07
    갔
    0.07
    줬
    0.07
    FAULT
    0.07
    сто
    0.07
    cep
    0.06
    Act Density 0.007%

    No Known Activations