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

    Neuronpedia

    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Powers
    -0.08
     Temper
    -0.08
     Negra
    -0.07
     Pelosi
    -0.07
     trecut
    -0.07
     universe
    -0.07
     mutual
    -0.07
    Throwable
    -0.07
    董事
    -0.07
    ────────
    -0.07
    POSITIVE LOGITS
     convertir
    0.11
     motorway
    0.10
     kilometers
    0.10
     vitesse
    0.10
     velocidade
    0.10
     conversions
    0.09
     Convert
    0.09
    Convert
    0.09
     convert
    0.09
     converted
    0.09
    Act Density 0.006%

    No Known Activations