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

    Neuronpedia

    INDEX
    Explanations

    after a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ꮸ
    0.56
    pubescens
    0.55
    Hydrochloride
    0.52
     बालकनियां
    0.52
     namani
    0.52
     químicos
    0.52
    Loksatta
    0.52
     SoaException
    0.52
    ඩු
    0.51
    getCQL
    0.50
    POSITIVE LOGITS
    ע
    0.79
     in
    0.74
    u
    0.68
    o
    0.66
    ق
    0.64
     and
    0.64
    el
    0.64
    א
    0.63
     the
    0.63
     will
    0.62
    Act Density 0.000%

    No Known Activations