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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     आख
    -0.07
     territor
    -0.07
     Writer
    -0.06
     Walter
    -0.06
    sız
    -0.06
    _ent
    -0.06
     slic
    -0.06
    _FP
    -0.06
     Η
    -0.06
    Bracket
    -0.06
    POSITIVE LOGITS
     프로
    0.07
    (argv
    0.07
    ologické
    0.06
    plx
    0.06
    -before
    0.06
    ploy
    0.06
    inou
    0.06
     prematurely
    0.06
     조
    0.06
     muscle
    0.06
    Act Density 0.002%

    No Known Activations