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

    Neuronpedia

    INDEX
    Explanations

    greater than mouth eating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nut
    0.41
    Nut
    0.40
     nutric
    0.40
     Nutritional
    0.39
    брать
    0.38
    ﹗
    0.37
     promoters
    0.37
    assess
    0.37
     basaltes
    0.37
    ब्रा
    0.37
    POSITIVE LOGITS
    レベル
    0.45
     always
    0.44
     PM
    0.44
    Always
    0.42
     завжди
    0.41
     Always
    0.40
     accomplishing
    0.39
    常に
    0.39
     ಯಾವಾಗ
    0.39
     всегда
    0.38
    Act Density 0.000%

    No Known Activations