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

    Neuronpedia

    INDEX
    Explanations

    listing items or etc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     candidat
    0.73
     kilomet
    0.71
     prere
    0.70
    engined
    0.68
    STARTED
    0.68
    <unused481>
    0.67
    龕
    0.67
    銠
    0.66
    ﺛ
    0.66
    トキ
    0.65
    POSITIVE LOGITS
     등이
    1.00
     등을
    0.96
     इत्यादि
    0.96
     etc
    0.95
    なども
    0.87
    などは
    0.84
    などを
    0.81
     등의
    0.81
     എന്നിവ
    0.81
    ...).
    0.81
    Act Density 0.258%

    No Known Activations