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

    Neuronpedia

    INDEX
    Explanations

    state of being

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     permettent
    0.60
     했는데
    0.58
     способствует
    0.57
     обеспечивает
    0.57
     zorgt
    0.55
     chcia
    0.54
     دیا۔
    0.53
     けど
    0.53
     permette
    0.52
     помогает
    0.52
    POSITIVE LOGITS
     remains
    0.96
     rests
    0.84
     lies
    0.80
     hinges
    0.75
     remain
    0.72
     warrants
    0.70
     appears
    0.70
     hasn
    0.66
     merits
    0.66
     falls
    0.66
    Act Density 0.710%

    No Known Activations