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

    Neuronpedia

    INDEX
    Explanations

    field

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ponential
    -0.07
    viewport
    -0.06
    element
    -0.06
    puter
    -0.06
    PASSWORD
    -0.06
     heartbreaking
    -0.06
    .Load
    -0.06
    ibbean
    -0.06
    egade
    -0.06
    css
    -0.06
    POSITIVE LOGITS
     Tig
    0.07
     inici
    0.07
     MSR
    0.07
     Тем
    0.06
     fj
    0.06
    技能
    0.06
    /big
    0.06
    Θ
    0.06
    (Il
    0.06
     dorsal
    0.06
    Act Density 0.001%

    No Known Activations