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

    Neuronpedia

    INDEX
    Explanations

    Cells

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    зь
    -0.07
    بية
    -0.07
    Plans
    -0.07
     uber
    -0.07
    Urban
    -0.06
    food
    -0.06
     breeding
    -0.06
    ushing
    -0.06
     Journey
    -0.06
    enerating
    -0.06
    POSITIVE LOGITS
    _LOCK
    0.07
    _ct
    0.06
     WIN
    0.06
     나를
    0.06
     udrž
    0.06
     دختر
    0.06
    ेर
    0.06
    _MONITOR
    0.06
     tri
    0.06
     nevě
    0.06
    Act Density 0.008%

    No Known Activations