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

    Neuronpedia

    INDEX
    Explanations

    obscure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    juan
    -0.07
    throp
    -0.07
    centroid
    -0.06
     Partnership
    -0.06
     célib
    -0.06
     governmental
    -0.06
     Twins
    -0.06
     zipper
    -0.06
     gelenek
    -0.06
     کیف
    -0.06
    POSITIVE LOGITS
     obscure
    0.16
     obscured
    0.11
     obsc
    0.10
     occult
    0.10
     arcane
    0.09
     obs
    0.08
     espresso
    0.07
    craft
    0.07
     obscene
    0.07
    _ctl
    0.07
    Act Density 0.004%

    No Known Activations