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

    Neuronpedia

    INDEX
    Explanations

    existence and movement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     takeaways
    0.75
     payoffs
    0.74
     EVERYTHING
    0.70
     причем
    0.68
     যেটা
    0.66
     하다
    0.63
     yourselves
    0.63
     nhé
    0.62
     talaga
    0.62
     questionnaires
    0.61
    POSITIVE LOGITS
    paras
    0.76
     subsp
    0.76
    เคลื่อน
    0.75
     protop
    0.72
    apparition
    0.72
     ethereal
    0.71
     pojav
    0.71
    companions
    0.71
     decap
    0.69
     prey
    0.68
    Act Density 0.035%

    No Known Activations