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

    Neuronpedia

    INDEX
    Explanations

    sunrise first

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     coats
    0.44
     Coat
    0.41
     compactly
    0.40
    ﺩ
    0.39
     homeomorphic
    0.39
    hwnd
    0.39
     "'"
    0.39
    ++;
    0.38
    ')))
    0.38
    背后
    0.38
    POSITIVE LOGITS
    bas
    0.42
    raya
    0.42
     surrog
    0.40
    🕝
    0.39
     ホ
    0.39
    ovým
    0.38
    🕤
    0.38
     stub
    0.38
    ovir
    0.37
     slum
    0.36
    Act Density 0.000%

    No Known Activations