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

    Neuronpedia

    INDEX
    Explanations

    philosophical/academic discussions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ації
    -0.07
    odb
    -0.06
    ує
    -0.06
    RICS
    -0.06
    效
    -0.06
    assadors
    -0.06
    uced
    -0.06
    parallel
    -0.06
    ycled
    -0.06
     anger
    -0.06
    POSITIVE LOGITS
     Gundam
    0.07
     Cumhur
    0.06
     digestion
    0.06
    .scheduler
    0.06
     прок
    0.06
    _SELECTED
    0.06
     Diablo
    0.06
     onMouse
    0.06
     Наг
    0.06
     entren
    0.06
    Act Density 0.158%

    No Known Activations