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

    Neuronpedia

    INDEX
    Explanations

    states of being

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vooral
    1.25
    собенно
    1.15
     특히
    1.12
     mooie
    1.08
     těž
    1.06
    などは
    1.06
     요즘
    1.04
     prachtige
    1.02
     особенно
    1.01
     물론
    1.00
    POSITIVE LOGITS
     during
    1.08
     instantaneously
    0.90
     यानी
    0.88
     thermodynam
    0.85
     information
    0.84
    During
    0.83
     म्हणजेच
    0.82
     During
    0.81
     transcriptional
    0.77
     when
    0.77
    Act Density 0.152%

    No Known Activations