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

    Neuronpedia

    INDEX
    Explanations

    something or thing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ف
    0.63
    ag
    0.58
    ad
    0.52
    nobody
    0.51
    ay
    0.50
    oll
    0.48
    م
    0.48
    ab
    0.47
    endrá
    0.46
    est
    0.46
    POSITIVE LOGITS
    መሪያ
    0.45
    getMetering
    0.45
    리면
    0.45
     Untersuch
    0.42
     도움
    0.42
    Accelerometer
    0.41
     Monat
    0.41
    г
    0.40
    𒊏
    0.40
    atically
    0.40
    Act Density 0.044%

    No Known Activations