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

    Neuronpedia

    INDEX
    Explanations

    h

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _war
    -0.07
    INCLUDING
    -0.06
     друж
    -0.06
    ερι
    -0.06
     деп
    -0.06
    				↵				↵
    -0.06
    OBJECT
    -0.06
    Av
    -0.06
     misery
    -0.06
    021
    -0.06
    POSITIVE LOGITS
     creado
    0.07
    gements
    0.07
    تباط
    0.07
     midi
    0.06
    렀
    0.06
    rc
    0.06
     Exactly
    0.06
    บ
    0.06
    셨
    0.06
     ($.
    0.06
    Act Density 0.019%

    No Known Activations