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

    Neuronpedia

    INDEX
    Explanations

    passing, passed, passage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ĝ
    0.65
    ρθρο
    0.64
    ито
    0.63
    ফিক
    0.63
     ज्वाइन
    0.62
    واعد
    0.61
     본격
    0.61
     méthodique
    0.61
    ))+\
    0.60
    rinos
    0.57
    POSITIVE LOGITS
     pass
    5.02
     passing
    4.96
    Pass
    4.89
     Pass
    4.76
     passes
    4.73
     passed
    4.70
    Passing
    4.64
     Passing
    4.64
    pass
    4.62
    passing
    4.50
    Act Density 0.586%

    No Known Activations