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

    Neuronpedia

    INDEX
    Explanations

    mobile links to youtube facebook blog

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ون
    0.77
    ত
    0.73
    י
    0.73
    ANCE
    0.70
    INES
    0.70
    ATION
    0.69
    ASER
    0.68
    ي
    0.66
    ש
    0.65
    א
    0.64
    POSITIVE LOGITS
    செய
    0.59
     உள்ளன
    0.57
    xt
    0.55
    ote
    0.54
    пара
    0.54
     ventaja
    0.53
    zieht
    0.52
    ště
    0.52
    orter
    0.51
    ateur
    0.51
    Act Density 0.003%

    No Known Activations