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

    Neuronpedia

    INDEX
    Explanations

    responding to prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ἑ
    0.48
    inputId
    0.46
    ayside
    0.46
    irt
    0.45
    innings
    0.45
     সেনাবাহিনীর
    0.44
    ending
    0.43
     каждом
    0.43
    äft
    0.42
    超
    0.42
    POSITIVE LOGITS
    ك
    0.54
     dims
    0.42
     Fiona
    0.40
     voluntad
    0.40
    വും
    0.40
     consciousness
    0.38
    बि
    0.38
     recib
    0.38
     scriv
    0.38
     poetry
    0.38
    Act Density 0.003%

    No Known Activations