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

    Neuronpedia

    INDEX
    Explanations

    social acceptance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ழை
    0.41
     आना
    0.35
     đăng
    0.35
    ᄊ
    0.35
     naš
    0.35
    pergillus
    0.35
    Ꮏ
    0.34
    <unused711>
    0.34
     finalised
    0.34
    秾
    0.34
    POSITIVE LOGITS
    PAM
    0.43
    Gambar
    0.42
     PAT
    0.40
     CASE
    0.39
    Case
    0.39
    。“
    0.39
     Case
    0.38
    ફો
    0.38
    ADOR
    0.38
    PAT
    0.38
    Act Density 0.000%

    No Known Activations