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

    Neuronpedia

    INDEX
    Explanations

    medical advice disclaimer

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    duğ
    0.59
    angga
    0.57
     আলোকিত
    0.56
    aughlin
    0.55
     й
    0.54
    --"
    0.54
    ULF
    0.53
    Attach
    0.52
    arl
    0.52
    ció
    0.52
    POSITIVE LOGITS
    펜
    0.69
    라운
    0.67
     Wyoming
    0.64
     vipp
    0.64
    فس
    0.59
     Raptor
    0.59
    ሸ
    0.59
    IMENT
    0.58
     IRL
    0.58
     PSE
    0.58
    Act Density 0.000%

    No Known Activations