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

    Neuronpedia

    INDEX
    Explanations

    academic texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    etsk
    -0.08
    getc
    -0.07
    rike
    -0.07
    xito
    -0.06
    اهر
    -0.06
     heroin
    -0.06
     ogs
    -0.06
    Style
    -0.06
    SEX
    -0.06
    igsaw
    -0.06
    POSITIVE LOGITS
    函数
    0.07
     Skywalker
    0.06
    =False
    0.06
    +#
    0.06
     Verb
    0.06
     annually
    0.06
    Phil
    0.06
     troublesome
    0.06
    iscrim
    0.06
    (master
    0.06
    Act Density 0.000%

    No Known Activations