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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ADOW
    -0.07
    imal
    -0.07
     suit
    -0.06
    ून
    -0.06
    suite
    -0.06
     maximal
    -0.06
    radius
    -0.06
    _mutex
    -0.06
    ÖL
    -0.06
    surface
    -0.06
    POSITIVE LOGITS
    อเร
    0.07
     �
    0.07
    械
    0.07
     गई
    0.06
    踏
    0.06
     hors
    0.06
    .LogWarning
    0.06
     AV
    0.06
     Мед
    0.06
     FBI
    0.06
    Act Density 0.026%

    No Known Activations