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

    Neuronpedia

    INDEX
    Explanations

    attentively, intently, number of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    usiasm
    1.07
    ために
    1.04
    anyahu
    1.01
     Zaj
    1.01
    player
    1.00
    ipkan
    1.00
    ὖ
    0.98
     धना
    0.97
    rukt
    0.96
     hạn
    0.96
    POSITIVE LOGITS
     hade
    0.98
     Monte
    0.96
    assy
    0.94
    Monte
    0.94
     করোনা
    0.93
     gesetz
    0.93
    ENTER
    0.92
    τερα
    0.91
    м
    0.90
    ICIO
    0.89
    Act Density 0.000%

    No Known Activations