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

    Neuronpedia

    INDEX
    Explanations

    Metroidvania, Monday, swimming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Scan
    0.50
     Neutral
    0.48
    mh
    0.47
    ва
    0.45
    畯
    0.44
     در
    0.44
    াম
    0.44
    ung
    0.43
    ك
    0.43
     Schon
    0.43
    POSITIVE LOGITS
     ने
    0.53
     spouse
    0.52
     bloodstream
    0.52
     ಚುನಾವಣ
    0.52
     doorway
    0.52
     waiver
    0.50
     professionally
    0.49
    ˨
    0.49
     doorstep
    0.48
     viol
    0.48
    Act Density 0.000%

    No Known Activations