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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vaginal
    -0.07
    Traditional
    -0.07
     getter
    -0.07
    irmingham
    -0.06
    овых
    -0.06
    RequestBody
    -0.06
     archetype
    -0.06
     toughest
    -0.06
    Secondary
    -0.06
     Nikol
    -0.06
    POSITIVE LOGITS
     pued
    0.06
     LUA
    0.06
     Mim
    0.06
    (goal
    0.06
    _RS
    0.06
     Kang
    0.06
     BITS
    0.06
     애
    0.06
     Ders
    0.06
    leur
    0.06
    Act Density 0.004%

    No Known Activations