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

    Neuronpedia

    INDEX
    Explanations

    based

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ButtonTitles
    -0.06
     Colonial
    -0.06
     Index
    -0.06
     fractures
    -0.06
     석
    -0.06
     affection
    -0.06
     knobs
    -0.06
    PFN
    -0.06
     spanking
    -0.06
     Υ
    -0.06
    POSITIVE LOGITS
    もり
    0.09
    calcul
    0.07
     speculate
    0.07
    ftp
    0.07
     dispersed
    0.07
    @extends
    0.06
    とする
    0.06
    сию
    0.06
    dn
    0.06
    __$
    0.06
    Act Density 0.006%

    No Known Activations