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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bypass
    -0.08
    brakk
    -0.07
    poly
    -0.07
    šov
    -0.07
    итет
    -0.06
    imates
    -0.06
    7
    -0.06
    3
    -0.06
    ۳۰
    -0.06
     Ish
    -0.06
    POSITIVE LOGITS
     Serena
    0.07
     cider
    0.07
    \Url
    0.07
     Ost
    0.06
    _DESC
    0.06
    (cert
    0.06
     shaving
    0.06
     Frau
    0.06
    에서
    0.06
     >",
    0.06
    Act Density 0.027%

    No Known Activations