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

    Neuronpedia

    INDEX
    Explanations

    melancholic, suspicion, beautification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    രുന്നു
    0.49
    🫢
    0.46
     மடங்கு
    0.46
    🌏
    0.46
     Гуляць
    0.45
     raging
    0.45
    😧
    0.45
     dreaded
    0.45
    érance
    0.45
    𝑍
    0.45
    POSITIVE LOGITS
     Mel
    0.49
     criar
    0.42
     watercolour
    0.41
     snails
    0.40
     be
    0.39
     watercolors
    0.38
     Laz
    0.38
     Mar
    0.38
     近
    0.37
    elf
    0.37
    Act Density 0.004%

    No Known Activations