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

    Neuronpedia

    INDEX
    Explanations

    harmful concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RetResult
    0.47
    চন্দ্রের
    0.47
     Caedwalla
    0.43
    জ্ঞান
    0.43
    டல்
    0.42
    СК
    0.42
    (!)
    0.41
     espectáculo
    0.40
     consecuencias
    0.40
    EME
    0.40
    POSITIVE LOGITS
    ancements
    0.49
    한
    0.42
    NT
    0.41
    ective
    0.41
    い
    0.41
     inspiring
    0.40
    тивних
    0.40
    ოვნ
    0.40
    itives
    0.40
    atifs
    0.39
    Act Density 0.007%

    No Known Activations