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

    Neuronpedia

    INDEX
    Explanations

    where

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Decrypt
    -0.07
     Encryption
    -0.07
    _th
    -0.06
    نين
    -0.06
     Jr
    -0.06
     poisonous
    -0.06
    .Comm
    -0.06
     fø
    -0.06
     doubts
    -0.06
    	hit
    -0.06
    POSITIVE LOGITS
    íl
    0.06
     Occ
    0.06
    0.06
    LAND
    0.06
    ี้
    0.06
     Monterey
    0.06
    handle
    0.06
    τουργ
    0.06
    inae
    0.06
    serir
    0.06
    Act Density 0.009%

    No Known Activations