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

    Neuronpedia

    INDEX
    Explanations

    High Priestess

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     funciona
    0.48
     questo
    0.48
     escribe
    0.46
     funziona
    0.45
     consigue
    0.45
     créé
    0.44
     sistem
    0.43
     rumor
    0.43
     systeem
    0.43
     smiley
    0.43
    POSITIVE LOGITS
    Massachusetts
    0.47
    хва
    0.47
    Colon
    0.45
    Atlant
    0.44
    setClass
    0.44
    फेसर
    0.43
    certain
    0.42
    Ｊ
    0.42
    were
    0.42
    ilitas
    0.41
    Act Density 0.003%

    No Known Activations