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

    Neuronpedia

    INDEX
    Explanations

    initial scale, event handling, previews

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Missy
    0.42
     glandes
    0.38
    𐰇
    0.37
    ষুধ
    0.36
     Hydrochloride
    0.35
     duckys
    0.35
     علیکم
    0.35
    玠
    0.35
    وبه
    0.34
    ঁচু
    0.34
    POSITIVE LOGITS
    S
    0.42
    s
    0.42
    ly
    0.40
    D
    0.39
    ing
    0.38
    id
    0.37
    и
    0.37
    i
    0.37
    I
    0.36
    ific
    0.36
    Act Density 0.036%

    No Known Activations