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

    Neuronpedia

    INDEX
    Explanations

    computer programs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     biology
    -0.29
     Biology
    -0.27
     liber
    -0.26
    æ³Į
    -0.26
     exploding
    -0.25
    ines
    -0.25
     lÃłnh
    -0.25
    å¹²éĥ¨éĺŁä¼į
    -0.24
     enrich
    -0.24
     pl
    -0.24
    POSITIVE LOGITS
    antic
    0.27
    å¿«
    0.26
    atical
    0.26
    osite
    0.25
    (Id
    0.25
    eco
    0.25
    延伸
    0.25
    usable
    0.25
     Nab
    0.24
     Grade
    0.24
    Act Density 0.013%

    No Known Activations