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

    Neuronpedia

    INDEX
    Explanations

    proportions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kitchen
    -0.07
    Return
    -0.07
    áb
    -0.07
     signal
    -0.07
    realm
    -0.06
    	time
    -0.06
     onchange
    -0.06
     Niagara
    -0.06
    insi
    -0.06
     amplified
    -0.06
    POSITIVE LOGITS
    しまった
    0.07
    getToken
    0.07
     واس
    0.06
     순간
    0.06
    '].$
    0.06
     Erk
    0.06
     торгів
    0.06
    ляється
    0.06
    _sqrt
    0.06
     =>$
    0.06
    Act Density 0.028%

    No Known Activations