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

    Neuronpedia

    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Carlo
    -0.07
    _intf
    -0.07
    (browser
    -0.06
    acent
    -0.06
     Empire
    -0.06
     longitudinal
    -0.06
    izik
    -0.06
    organizations
    -0.06
    شنبه
    -0.06
     plist
    -0.06
    POSITIVE LOGITS
    aaaaaaaa
    0.07
     dumb
    0.07
    ________________________________________________________________
    0.06
    anoi
    0.06
    <Key
    0.06
     stemming
    0.06
    CEEDED
    0.06
     nợ
    0.06
    cka
    0.06
    _BGR
    0.06
    Act Density 0.377%

    No Known Activations