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

    Neuronpedia

    INDEX
    Explanations

    file permissions (rwx)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]}.
    0.68
    rowset
    0.64
    atrième
    0.64
    𝒜
    0.64
    ا
    0.63
    ᴛ
    0.63
    HWND
    0.63
     focussed
    0.63
     collaborated
    0.62
     rested
    0.62
    POSITIVE LOGITS
    end
    0.54
    canc
    0.54
    і
    0.53
    뻣
    0.51
    c
    0.49
    I
    0.48
    ents
    0.48
    Uncle
    0.48
     zapis
    0.48
    '
    0.46
    Act Density 0.001%

    No Known Activations