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

    Neuronpedia

    INDEX
    Explanations

    promoting hatred and discrimination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᄄ
    0.48
    ర్లు
    0.46
     παρου
    0.45
     αξ
    0.44
    喍
    0.44
     angezeigt
    0.44
     ɛ
    0.43
     dredged
    0.43
     IMAGE
    0.43
     ብዙ
    0.43
    POSITIVE LOGITS
    -
    0.57
    St
    0.48
    For
    0.46
     Modular
    0.45
    .
    0.45
    Modular
    0.45
    ake
    0.44
     for
    0.44
    ↵↵
    0.43
     be
    0.43
    Act Density 0.009%

    No Known Activations