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

    Neuronpedia

    INDEX
    Explanations

    high

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    חנו
    0.92
     प्रभावों
    0.85
     gameOver
    0.83
     веществ
    0.81
     Veter
    0.79
    ínas
    0.78
    Ꮞ
    0.78
    咫
    0.77
     दिग्
    0.76
    された
    0.76
    POSITIVE LOGITS
     altitude
    1.30
    lighting
    1.28
     octane
    1.21
     altitudes
    1.14
     enough
    1.13
     voltage
    1.12
    altitude
    1.11
     priority
    1.11
    pitched
    1.11
     pitched
    1.08
    Act Density 0.201%

    No Known Activations