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

    Neuronpedia

    INDEX
    Explanations

    singularities, buyer protection, thoughts within, time machine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     naturally
    0.48
     spirituality
    0.43
     canonically
    0.41
     classically
    0.39
    ẹt
    0.38
     drawer
    0.38
     functionally
    0.38
     hypo
    0.38
     hydrating
    0.38
     compatible
    0.37
    POSITIVE LOGITS
     tõ
    0.40
     Conselho
    0.40
    ittees
    0.39
     Dispon
    0.39
     disposiciones
    0.39
    pessoa
    0.38
    issionais
    0.38
     පෙ
    0.37
     göster
    0.37
    ֮
    0.37
    Act Density 0.000%

    No Known Activations