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

    Neuronpedia

    INDEX
    Explanations

    as intended or expected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     password
    0.47
     agenda
    0.45
     descendant
    0.43
     message
    0.43
     score
    0.43
     PRES
    0.42
     SCORE
    0.42
     attitude
    0.42
     clues
    0.42
     revela
    0.42
    POSITIVE LOGITS
    স্ফ
    0.41
     Springs
    0.41
    PrefabAsset
    0.40
    ersburg
    0.39
    tbody
    0.39
    èmes
    0.38
    🛁
    0.38
    çük
    0.38
    öz
    0.38
    があり
    0.37
    Act Density 0.001%

    No Known Activations