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

    Neuronpedia

    INDEX
    Explanations

    sw

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Popular
    -0.07
     ipsum
    -0.07
    uffix
    -0.07
    pires
    -0.07
    HIP
    -0.07
    cript
    -0.07
     acción
    -0.07
     Corinth
    -0.07
    ensitive
    -0.07
     ingenious
    -0.07
    POSITIVE LOGITS
     sw
    0.14
     Sw
    0.13
     SW
    0.11
     swarm
    0.10
     Swan
    0.10
    -sw
    0.10
    (sw
    0.10
    Sw
    0.09
     Schwartz
    0.09
     swagger
    0.09
    Act Density 0.028%

    No Known Activations