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

    Neuronpedia

    INDEX
    Explanations

    intensified negation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    応援
    0.72
    ড়ী
    0.67
    стіше
    0.66
     volgende
    0.66
    ീയ
    0.66
    льт
    0.65
    ഴിഞ്ഞ
    0.65
    注意
    0.65
    ந்திய
    0.64
    ይ
    0.64
    POSITIVE LOGITS
     whatsoever
    2.73
     вообще
    2.15
     überhaupt
    1.98
     altogether
    1.82
     вовсе
    1.77
     at
    1.70
     совсем
    1.66
     전혀
    1.53
     assolutamente
    1.52
    เลย
    1.51
    Act Density 0.120%

    No Known Activations