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

    Neuronpedia

    INDEX
    Explanations

    mixture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _HT
    -0.07
     Mongolia
    -0.07
     staggering
    -0.06
    IW
    -0.06
     lodge
    -0.06
    557
    -0.06
     tk
    -0.06
     battered
    -0.06
     commented
    -0.06
    scaling
    -0.06
    POSITIVE LOGITS
    _output
    0.07
    ahaha
    0.06
     окрем
    0.06
    	sprintf
    0.06
     أق
    0.06
    (Post
    0.06
     maxSize
    0.06
     getObject
    0.06
    -between
    0.06
    ây
    0.06
    Act Density 0.121%

    No Known Activations