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

    Neuronpedia

    INDEX
    Explanations

    non

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ọt
    -0.07
     seats
    -0.06
    _DATA
    -0.06
     suất
    -0.06
    DC
    -0.06
     dictionaries
    -0.06
     Hilton
    -0.06
    ぞ
    -0.06
     kvinna
    -0.06
     retailer
    -0.06
    POSITIVE LOGITS
    ΟΝ
    0.07
     careless
    0.06
     Jerome
    0.06
    "]/
    0.06
     closeButton
    0.06
    (Response
    0.06
    Mid
    0.06
     كرد
    0.06
    [attr
    0.06
     Listening
    0.06
    Act Density 0.011%

    No Known Activations