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

    Neuronpedia

    INDEX
    Explanations

    abbreviations or acronyms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    विषयी
    0.46
     Rebek
    0.45
    ían
    0.45
    ंपरा
    0.45
     bygone
    0.44
     jiné
    0.44
     foresight
    0.44
     reconsider
    0.41
     bedside
    0.40
     skillful
    0.40
    POSITIVE LOGITS
    IS
    0.63
    IL
    0.58
    EL
    0.57
    W
    0.56
    J
    0.54
    IG
    0.54
    U
    0.54
    ER
    0.51
    SS
    0.51
    IN
    0.50
    Act Density 0.045%

    No Known Activations