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

    Neuronpedia

    INDEX
    Explanations

    Creative Mode, Direct Connect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     boiling
    0.46
    れて
    0.44
     KOH
    0.43
     enhances
    0.42
     juggling
    0.42
     parity
    0.40
    slim
    0.40
    '
    0.39
     Eisen
    0.39
     antioxidants
    0.39
    POSITIVE LOGITS
    আপনার
    0.49
     можли
    0.48
    巌
    0.47
     계약
    0.45
     compliqué
    0.44
    可能的
    0.44
    𝐒
    0.44
     communiqué
    0.43
    可能
    0.42
    Попис
    0.42
    Act Density 0.045%

    No Known Activations