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

    Neuronpedia

    INDEX
    Explanations

    using System;

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    を迎
    0.49
    คอง
    0.46
     domicilio
    0.46
    ovll
    0.44
     cazul
    0.44
     अधीनस्थ
    0.44
     चौंका
    0.43
     duelo
    0.43
    merksam
    0.42
     tabella
    0.42
    POSITIVE LOGITS
    BI
    0.43
    PAY
    0.43
    DAY
    0.43
    Air
    0.41
    EX
    0.41
     Announced
    0.41
    scale
    0.40
     பாலை
    0.40
    Δ
    0.40
     ứng
    0.40
    Act Density 0.000%

    No Known Activations