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

    Neuronpedia

    INDEX
    Explanations

    news events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Automation
    -0.06
    .same
    -0.06
     oblast
    -0.06
    ILLISE
    -0.06
     diffuse
    -0.06
     IS
    -0.06
    。如果
    -0.06
    Versions
    -0.06
     valid
    -0.06
    _find
    -0.05
    POSITIVE LOGITS
     Ging
    0.07
     спіл
    0.07
     causes
    0.07
     absence
    0.06
    ию
    0.06
    abra
    0.06
     smoothing
    0.06
    RTC
    0.06
    ิโล
    0.06
    ný
    0.06
    Act Density 0.000%

    No Known Activations