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

    Neuronpedia

    INDEX
    Explanations

    research initiatives and patients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rot
    0.40
    faith
    0.39
     confidence
    0.39
     conta
    0.38
     faith
    0.38
     reacts
    0.37
     rep
    0.37
     perceptions
    0.37
    maker
    0.37
    rep
    0.37
    POSITIVE LOGITS
     dedicar
    0.43
     Kya
    0.42
     čty
    0.42
     gastron
    0.40
    xRt
    0.40
     आईटी
    0.40
     mmf
    0.39
     aquella
    0.39
    երը
    0.39
    erset
    0.39
    Act Density 0.008%

    No Known Activations