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

    Neuronpedia

    INDEX
    Explanations

    arising out of, rising over

    np_acts-logits-general · gemini-2.5-flash-lite

    things change, flow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    с
    0.72
    ated
    0.68
    ira
    0.67
    uting
    0.66
    elling
    0.66
    ried
    0.65
    raising
    0.64
    ys
    0.62
    iling
    0.62
    ending
    0.60
    POSITIVE LOGITS
    u
    0.78
     de
    0.74
    Ğ
    0.71
     interfaz
    0.68
     excell
    0.67
    ከሰ
    0.66
     internationaux
    0.65
    ಮ
    0.65
    োড
    0.64
    ール
    0.64
    Act Density 1.957%

    No Known Activations