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

    Neuronpedia

    INDEX
    Explanations

    wave amplitude sinusoidal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     каз
    0.72
     शू
    0.72
     Goblin
    0.72
     Cappadocia
    0.70
     deadlock
    0.66
     રાખ
    0.66
    ჩევ
    0.65
     Merlot
    0.65
     gamer
    0.65
     Kakkar
    0.65
    POSITIVE LOGITS
     Amplitude
    1.98
     amplitude
    1.98
    Amplitude
    1.91
     waves
    1.91
    amplitude
    1.82
     amplitudes
    1.82
     sinusoidal
    1.79
    Wave
    1.77
     wave
    1.76
     Wave
    1.76
    Act Density 0.372%

    No Known Activations