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

    Neuronpedia

    INDEX
    Explanations

    URLs and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.38
    ↵↵
    0.30
     Dr
    0.30
     Allies
    0.29
    ↵
    0.28
     Dinge
    0.28
     D
    0.27
     Zeit
    0.27
     Niet
    0.27
     Boston
    0.27
    POSITIVE LOGITS
     ቀለም
    0.29
     multiSelectList
    0.29
     popOperand
    0.28
     chmod
    0.28
    Tabuleiro
    0.27
    薏
    0.27
    humidité
    0.26
    మ్
    0.26
    mxCell
    0.26
    秸
    0.26
    Act Density 0.001%

    No Known Activations