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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    umble
    -0.06
     μπο
    -0.06
    NavigationBar
    -0.06
     Від
    -0.06
     컴
    -0.06
     Annotation
    -0.06
     roses
    -0.06
    Bonus
    -0.06
     Reynolds
    -0.06
    рав
    -0.06
    POSITIVE LOGITS
    :index
    0.07
    (Func
    0.06
     Android
    0.06
     جدا
    0.06
    035
    0.06
    ítica
    0.06
    :].
    0.06
    FromFile
    0.06
    IRM
    0.06
     feminist
    0.06
    Act Density 0.082%

    No Known Activations