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

    Neuronpedia

    INDEX
    Explanations

    Names and places

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ilene
    -1.07
    imus
    -0.99
    itance
    -0.64
    autoreleasepool
    -0.59
    ReusableCell
    -0.58
    mical
    -0.56
    توض
    -0.52
    ädie
    -0.50
    SerializedSize
    -0.50
     mérite
    -0.50
    POSITIVE LOGITS
    y
    0.73
    TargetException
    0.67
     kasarigan
    0.57
     kaynağından
    0.52
    en
    0.51
    ExtendWith
    0.51
    ogast
    0.50
     Bray
    0.50
    ke
    0.49
    prof
    0.49
    Act Density 0.120%

    No Known Activations