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

    Neuronpedia

    INDEX
    Explanations

    paid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quits
    -0.07
     São
    -0.07
     wol
    -0.06
     convo
    -0.06
     nad
    -0.06
     jorn
    -0.06
    Sentence
    -0.06
    ỏ
    -0.06
     Tree
    -0.06
     Wind
    -0.06
    POSITIVE LOGITS
    .Exp
    0.07
    .Params
    0.07
    (comb
    0.06
    	common
    0.06
    _Err
    0.06
    _From
    0.06
    恋
    0.06
    @click
    0.06
    (reg
    0.06
    [model
    0.06
    Act Density 0.028%

    No Known Activations