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

    Neuronpedia

    INDEX
    Explanations

    verifying authenticity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    losure
    -0.07
     tâm
    -0.07
    .last
    -0.07
     RD
    -0.06
     Tao
    -0.06
    wav
    -0.06
     dri
    -0.06
     Kl
    -0.06
    range
    -0.06
     Kaz
    -0.06
    POSITIVE LOGITS
    icontains
    0.07
     honest
    0.07
     allowing
    0.07
     gratuitement
    0.06
     Apollo
    0.06
     safezone
    0.06
    ósito
    0.06
    METHOD
    0.06
    ώ
    0.06
    銀
    0.06
    Act Density 0.024%

    No Known Activations