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

    Neuronpedia

    INDEX
    Explanations

    reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Doming
    -0.06
     volcan
    -0.06
     resid
    -0.06
     Evangel
    -0.06
     bik
    -0.06
     Persons
    -0.06
    ateg
    -0.06
     TIMER
    -0.06
     intimidate
    -0.06
    oley
    -0.06
    POSITIVE LOGITS
    .setting
    0.07
    PWD
    0.06
    typeparam
    0.06
     Furthermore
    0.06
    "profile
    0.06
    −
    0.06
     wrench
    0.06
     #$
    0.06
     duyệt
    0.06
    _LICENSE
    0.06
    Act Density 0.086%

    No Known Activations