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

    Neuronpedia

    INDEX
    Explanations

    danger and absence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     suoi
    0.45
     byla
    0.44
    چل
    0.43
     অনুযায়ী
    0.43
    jsko
    0.43
    💤
    0.42
    いました
    0.42
     juggling
    0.42
    🥱
    0.42
     був
    0.41
    POSITIVE LOGITS
     불안
    0.48
     भय
    0.47
     fearful
    0.41
     위험
    0.40
    恐惧
    0.40
     fear
    0.40
     anxieties
    0.40
     reacting
    0.39
    惧
    0.39
    াহিদ
    0.39
    Act Density 0.000%

    No Known Activations