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

    Neuronpedia

    INDEX
    Explanations

    force

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     budouc
    -0.07
     tady
    -0.06
     banco
    -0.06
     Fits
    -0.06
    loven
    -0.06
    Animate
    -0.06
    _VENDOR
    -0.06
     filtro
    -0.06
     reserva
    -0.06
    koli
    -0.06
    POSITIVE LOGITS
    ैज
    0.08
     이는
    0.07
     Satan
    0.07
     توص
    0.06
    ски
    0.06
    地球
    0.06
     και
    0.06
    atan
    0.06
     Pierre
    0.06
    trip
    0.06
    Act Density 0.086%

    No Known Activations