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

    Neuronpedia

    INDEX
    Explanations

    first state or condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    יש
    0.51
    溇
    0.48
    ೩
    0.47
    🔍
    0.47
    renerg
    0.46
     بیاکتنې
    0.46
    ாரின்
    0.46
     ಆರೋಗ್ಯ
    0.45
     பயன்படுத்து
    0.45
     दोन्ही
    0.45
    POSITIVE LOGITS
    n
    0.51
    x
    0.50
     उम्मीद
    0.47
     Unreal
    0.46
     expectations
    0.46
     photons
    0.45
     improb
    0.44
     Demi
    0.43
     amass
    0.43
     pions
    0.43
    Act Density 0.007%

    No Known Activations