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

    Neuronpedia

    INDEX
    Explanations

    goto

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incompetence
    -0.06
     calculated
    -0.06
    CY
    -0.06
     framed
    -0.06
     Созд
    -0.06
     Asians
    -0.06
    κυ
    -0.06
     biçimde
    -0.06
     hé
    -0.06
     якщо
    -0.06
    POSITIVE LOGITS
    ')){↵
    0.07
    .visualization
    0.06
     知
    0.06
    .Reporting
    0.06
    urbation
    0.06
    ини
    0.06
    _SHIFT
    0.06
    اسیون
    0.06
     Lisp
    0.06
    áo
    0.06
    Act Density 0.001%

    No Known Activations