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

    Neuronpedia

    INDEX
    Explanations

    formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Unicode
    -0.06
    .windows
    -0.06
     números
    -0.06
     unicode
    -0.06
     concentr
    -0.06
     Nonetheless
    -0.06
     시간
    -0.06
    PASSWORD
    -0.06
    แป
    -0.06
    -ranked
    -0.06
    POSITIVE LOGITS
    ertil
    0.07
    dojo
    0.07
     maxx
    0.07
     wrest
    0.07
     баж
    0.06
     nargin
    0.06
     obtains
    0.06
    _ISS
    0.06
    Jones
    0.06
     Ellis
    0.06
    Act Density 0.035%

    No Known Activations