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

    Neuronpedia

    INDEX
    Explanations

    5

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bölümü
    -0.07
    сли
    -0.07
    business
    -0.07
     super
    -0.07
    ความ
    -0.07
    슥
    -0.07
     whole
    -0.07
    资本
    -0.06
    ♾
    -0.06
    .data
    -0.06
    POSITIVE LOGITS
    Executing
    0.07
    _traits
    0.07
    frey
    0.07
     אית
    0.07
    _off
    0.07
    -id
    0.07
     stunt
    0.07
    驾校
    0.07
     )↵↵↵↵↵↵↵↵
    0.07
    	N
    0.06
    Act Density 0.003%

    No Known Activations