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

    Neuronpedia

    INDEX
    Explanations

    correcting before escalation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    0.47
     паци
    0.45
    umon
    0.45
    annt
    0.44
    anc
    0.44
    有一些
    0.43
    un
    0.43
     संख
    0.43
    range
    0.42
     попробовать
    0.42
    POSITIVE LOGITS
     chip
    0.51
    HttpSession
    0.49
     fundraising
    0.48
    േന
    0.46
    の
    0.46
     league
    0.45
    せ
    0.44
     town
    0.44
     grave
    0.44
     manager
    0.43
    Act Density 0.000%

    No Known Activations