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

    Neuronpedia

    INDEX
    Explanations

    medical discomfort/side effects

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _tweet
    -0.08
    .aspx
    -0.07
    /power
    -0.07
     bumper
    -0.07
     citizenship
    -0.07
    _primary
    -0.06
    reshape
    -0.06
    -----
    -0.06
     licence
    -0.06
     touches
    -0.06
    POSITIVE LOGITS
    /G
    0.06
    cop
    0.06
     Díky
    0.06
    gos
    0.06
    akest
    0.06
    rå
    0.06
     Scouts
    0.06
     záz
    0.06
     มห
    0.06
     Async
    0.06
    Act Density 0.033%

    No Known Activations