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

    Neuronpedia

    INDEX
    Explanations

    ymb

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .course
    -0.07
    vens
    -0.07
    izzes
    -0.06
    λό
    -0.06
    -turn
    -0.06
    578
    -0.06
    Scheduler
    -0.06
     موضوع
    -0.06
    纯
    -0.06
    ्
    -0.06
    POSITIVE LOGITS
    Safety
    0.07
    _CAPTURE
    0.07
     receptions
    0.06
    (call
    0.06
     graduate
    0.06
     Fot
    0.06
     impacting
    0.06
    umat
    0.06
    _sep
    0.06
    .error
    0.06
    Act Density 0.001%

    No Known Activations