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

    Neuronpedia

    INDEX
    Explanations

    introductions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wan
    -0.07
    ǐ
    -0.07
    UGIN
    -0.06
    Their
    -0.06
    //(
    -0.06
     hei
    -0.06
     Petroleum
    -0.06
     beat
    -0.06
    vana
    -0.06
    Containers
    -0.06
    POSITIVE LOGITS
     nex
    0.08
    .INTEGER
    0.06
     PB
    0.06
     alpha
    0.06
    _FOLLOW
    0.06
     navigationController
    0.06
     xnxx
    0.06
    lédl
    0.06
    Allows
    0.06
     honorable
    0.06
    Act Density 0.097%

    No Known Activations