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

    Neuronpedia

    INDEX
    Explanations

    appearances

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _pw
    -0.07
    _esc
    -0.06
    _LOCAL
    -0.06
    CONFIG
    -0.06
    Compute
    -0.06
    Toy
    -0.06
    enant
    -0.06
    Software
    -0.06
    	put
    -0.06
    ↵
↵
↵
↵
    -0.06
    POSITIVE LOGITS
    .mContext
    0.07
    كيب
    0.07
    [op
    0.06
     harmful
    0.06
     meny
    0.06
    년
    0.06
    >i
    0.06
     CAPITAL
    0.06
     godt
    0.06
    แหน
    0.06
    Act Density 0.353%

    No Known Activations