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

    Neuronpedia

    INDEX
    Explanations

    Arthur Penhaligon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ю
    0.56
     Provider
    0.55
     numerator
    0.55
    ća
    0.54
    ga
    0.54
    Quest
    0.52
    㖵
    0.52
     Pubmed
    0.52
    㡱
    0.52
    ☝
    0.51
    POSITIVE LOGITS
    ون
    0.55
    os
    0.54
    solving
    0.50
    iski
    0.50
    ed
    0.49
    slash
    0.48
    hone
    0.48
     যেমন
    0.48
    ິ
    0.48
     hone
    0.47
    Act Density 0.000%

    No Known Activations