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

    Neuronpedia

    INDEX
    Explanations

    inquiring about you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    adata
    0.42
     вовсе
    0.41
    erosene
    0.40
    Ⲑ
    0.39
    '',
    0.39
    ğinden
    0.38
    უნქ
    0.38
    odată
    0.38
     conseguenza
    0.38
     consequências
    0.38
    POSITIVE LOGITS
    い
    0.41
     ]
    0.39
    insert
    0.38
    &
    0.37
     fő
    0.35
     flap
    0.35
    እ
    0.35
    ಈ
    0.35
    <sup>
    0.34
    arrive
    0.34
    Act Density 0.061%

    No Known Activations