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

    Neuronpedia

    INDEX
    Explanations

    role playing, reversal, prompt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ធ្វ
    0.40
    regulars
    0.40
     स्केल
    0.39
    rown
    0.39
    rams
    0.38
     personnelles
    0.38
     கிரே
    0.38
    rugg
    0.38
     белән
    0.37
     Rfd
    0.37
    POSITIVE LOGITS
    を果た
    0.80
     निभाने
    0.75
     played
    0.73
    Played
    0.70
    扮演
    0.70
    played
    0.68
     Played
    0.65
     निभा
    0.63
     roles
    0.61
     역할
    0.60
    Act Density 0.019%

    No Known Activations