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

    Neuronpedia

    INDEX
    Explanations

    math and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /method
    -0.07
    (jLabel
    -0.07
    Ban
    -0.06
     repost
    -0.06
     jednotlivých
    -0.06
     pres
    -0.06
    잡
    -0.06
     gerekmektedir
    -0.06
    ompiler
    -0.06
    --------------------
    -0.06
    POSITIVE LOGITS
     readme
    0.07
     sk
    0.07
     Pence
    0.07
     canvas
    0.06
     neon
    0.06
     cosmic
    0.06
     bat
    0.06
     parks
    0.06
    lernen
    0.06
     Caj
    0.06
    Act Density 0.044%

    No Known Activations