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

    Neuronpedia

    INDEX
    Explanations

    formatting elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    㐫
    0.80
     oligos
    0.80
     cbd
    0.76
    pod
    0.75
    ולים
    0.74
    Mehr
    0.74
     संबद्ध
    0.74
    臧
    0.74
    ມາ
    0.73
    ндары
    0.73
    POSITIVE LOGITS
     style
    0.71
     markdown
    0.65
     ImageIcon
    0.64
     Markdown
    0.63
    дент
    0.63
    IsMethod
    0.62
     indentation
    0.61
     ema
    0.60
     pavement
    0.60
     grout
    0.60
    Act Density 0.087%

    No Known Activations