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

    Neuronpedia

    INDEX
    Explanations

    even when, even with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    含む
    0.48
    Fragments
    0.46
     있죠
    0.45
     fume
    0.43
     fragments
    0.42
    ോളിക
    0.42
    Jis
    0.42
    fragments
    0.41
    的海
    0.41
    denominator
    0.41
    POSITIVE LOGITS
    urities
    0.48
     IMAX
    0.47
     consultative
    0.46
     консульта
    0.45
     Independ
    0.44
    ubern
    0.43
     Greatest
    0.43
     Georgetown
    0.42
    ATORY
    0.42
     संयोग
    0.42
    Act Density 0.001%

    No Known Activations