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

    Neuronpedia

    INDEX
    Explanations

    say "the ending -roid"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Notice
    -0.06
    blood
    -0.06
     borrow
    -0.06
     build
    -0.06
    Ot
    -0.06
    acted
    -0.06
     basement
    -0.06
    In
    -0.06
    calls
    -0.06
    _lower
    -0.06
    POSITIVE LOGITS
    ",__
    0.07
    	TokenNameIdentifier
    0.07
     Ευ
    0.07
     přech
    0.07
    ycastle
    0.07
    xampp
    0.07
     Philippe
    0.07
    _UTF
    0.07
     وسلم
    0.06
     жир
    0.06
    Act Density 0.029%

    No Known Activations