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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ;-
    -0.07
     studio
    -0.07
     premiere
    -0.07
    still
    -0.07
     }
↵
↵
↵
    -0.07
    ضبط
    -0.07
    _EXECUTE
    -0.07
    启示
    -0.06
     infant
    -0.06
    膳食
    -0.06
    POSITIVE LOGITS
    wright
    0.08
    CHEMY
    0.07
     orientations
    0.07
    ｬ
    0.07
    海南省
    0.07
    鹴
    0.07
     counselors
    0.07
    ありが
    0.07
     perverse
    0.07
    责任制
    0.07
    Act Density 0.001%

    No Known Activations