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

    Neuronpedia

    INDEX
    Explanations

    works

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Outstanding
    -0.06
     broth
    -0.06
     法
    -0.06
    entifier
    -0.06
    улю
    -0.06
     specified
    -0.06
     threshold
    -0.06
    \AppData
    -0.06
    yang
    -0.06
     AndAlso
    -0.06
    POSITIVE LOGITS
    aines
    0.07
    .cat
    0.06
    _lineno
    0.06
    ة
    0.06
    oky
    0.06
    is
    0.06
    ्रश
    0.06
     talents
    0.06
     kali
    0.06
    -trash
    0.06
    Act Density 0.000%

    No Known Activations