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

    Neuronpedia

    INDEX
    Explanations

    voice messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kanggo
    0.63
     privind
    0.57
     bellissimo
    0.57
     sehen
    0.52
     printemps
    0.52
     démontrer
    0.50
     que
    0.50
    emb
    0.49
     qué
    0.49
     deze
    0.49
    POSITIVE LOGITS
     लक्ष्य
    0.51
     확실
    0.49
     مل
    0.47
     پہ
    0.45
    snapshot
    0.45
    isture
    0.45
     समी
    0.44
     항
    0.44
    aaf
    0.44
    也好
    0.43
    Act Density 0.000%

    No Known Activations