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

    Neuronpedia

    INDEX
    Explanations

    underground

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Project
    -0.08
     perpendicular
    -0.08
    יצוב
    -0.08
     केले
    -0.08
     अक्ष
    -0.08
    studio
    -0.08
    dam
    -0.08
    inam
    -0.08
     Thanksgiving
    -0.08
     estratég
    -0.08
    POSITIVE LOGITS
     shady
    0.11
     illicit
    0.11
     clandest
    0.10
     criminal
    0.09
     unauthorized
    0.09
     крим
    0.09
     преступ
    0.09
     underground
    0.09
    非法
    0.08
     subterr
    0.08
    Act Density 0.019%

    No Known Activations