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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ിരുന്ന
    -0.08
    enda
    -0.08
     informacje
    -0.07
     edece
    -0.07
    blicke
    -0.07
    ేష
    -0.07
    /render
    -0.07
    шага
    -0.07
    ર્મ
    -0.07
    రీక్ష
    -0.07
    POSITIVE LOGITS
     obviously
    0.09
     phải
    0.08
     obvious
    0.08
     Nature
    0.08
     meant
    0.08
     løs
    0.08
     meteen
    0.08
     zomaar
    0.07
    Indonesia
    0.07
     হার
    0.07
    Act Density 0.031%

    No Known Activations