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

    Neuronpedia

    INDEX
    Explanations

    code and URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     arrested
    -0.07
     David
    -0.07
     molto
    -0.06
    	float
    -0.06
     sorry
    -0.06
     Sarah
    -0.06
     admits
    -0.06
     qed
    -0.06
    (AP
    -0.06
    datetime
    -0.06
    POSITIVE LOGITS
     округ
    0.07
    TableViewCell
    0.07
    яется
    0.06
    legation
    0.06
    ?$
    0.06
    iei
    0.06
    _rl
    0.06
    ACING
    0.06
    _EXTERNAL
    0.06
    <=$
    0.06
    Act Density 0.062%

    No Known Activations