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

    Neuronpedia

    INDEX
    Explanations

    service query

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    at
    0.35
    as
    0.32
    asting
    0.31
    न
    0.30
    б
    0.29
    irs
    0.29
    一批
    0.29
    entre
    0.28
    й
    0.28
    ই
    0.28
    POSITIVE LOGITS
     comprobar
    0.33
     влияет
    0.32
     charset
    0.32
     waterway
    0.32
     tp
    0.31
    ITAR
    0.31
     ఆఫ్
    0.31
    ⇔
    0.31
     pter
    0.30
     überprüfen
    0.30
    Act Density 0.149%

    No Known Activations