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

    Neuronpedia

    INDEX
    Explanations

    a [adjective/noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Y
    1.13
    ED
    1.10
     którzy
    1.09
    ING
    1.09
     theſe
    1.04
    .¹
    0.98
    ed
    0.95
    юсь
    0.94
     zestaw
    0.93
     besie
    0.93
    POSITIVE LOGITS
    ก
    1.12
    na
    1.02
    க்
    1.01
    후
    0.96
    0.95
    さて
    0.91
    يمة
    0.91
    ح
    0.89
     nyata
    0.89
    на
    0.88
    Act Density 0.656%

    No Known Activations