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

    Neuronpedia

    INDEX
    Explanations

    Results

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    strument
    -0.07
    AN
    -0.07
    SplitOptions
    -0.07
    伏
    -0.07
     Mastery
    -0.06
     ingres
    -0.06
     Monitoring
    -0.06
    ety
    -0.06
    ัพท
    -0.06
     fertilizer
    -0.06
    POSITIVE LOGITS
    common
    0.07
    �
    0.07
     rocker
    0.06
     glimps
    0.06
    estimate
    0.06
     speaker
    0.06
     encountered
    0.06
    *a
    0.06
    .Name
    0.06
     жизнь
    0.06
    Act Density 0.491%

    No Known Activations