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

    Neuronpedia

    INDEX
    Explanations

    programming commands

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⅲ
    0.76
    ccnc
    0.69
     rpg
    0.69
     Sms
    0.68
    mlp
    0.68
     Psp
    0.68
    न्दावन
    0.68
     ahuv
    0.67
     cds
    0.66
     Cdc
    0.66
    POSITIVE LOGITS
    INT
    1.52
     INT
    1.50
    END
    1.48
     SUB
    1.46
     POST
    1.45
     SET
    1.43
     DATE
    1.43
     PRO
    1.42
     CON
    1.41
    POST
    1.41
    Act Density 0.823%

    No Known Activations