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

    Neuronpedia

    INDEX
    Explanations

    lists of items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     methylation
    0.45
     कैल्शियम
    0.45
    کروچ
    0.44
     fixe
    0.44
    صیٰ
    0.44
     frosts
    0.43
     yeasts
    0.43
     snippetHide
    0.42
     dispensers
    0.40
     frais
    0.40
    POSITIVE LOGITS
    am
    0.49
     Z
    0.46
    g
    0.44
    row
    0.44
     D
    0.44
    ire
    0.43
     Facts
    0.43
     admiration
    0.42
    re
    0.42
    ll
    0.42
    Act Density 0.001%

    No Known Activations