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

    Neuronpedia

    INDEX
    Explanations

    let's introductions and commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Although
    0.71
    although
    0.64
    أ
    0.59
    How
    0.58
    Because
    0.58
    Dis
    0.57
    えています
    0.57
    אן
    0.55
    是如何
    0.55
     如何
    0.55
    POSITIVE LOGITS
     them
    1.18
     us
    1.03
     it
    0.98
     things
    0.96
     him
    0.93
     انہیں
    0.90
     me
    0.86
     outsiders
    0.84
     त्यांना
    0.83
     undue
    0.82
    Act Density 0.708%

    No Known Activations