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

    Neuronpedia

    INDEX
    Explanations

    improving or categorizing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mia
    0.52
     trent
    0.47
     fn
    0.44
     vera
    0.43
     feedback
    0.42
    った
    0.40
     immun
    0.40
     processor
    0.39
     numéro
    0.38
     fitur
    0.38
    POSITIVE LOGITS
    SOI
    0.49
    yearly
    0.48
    Jdk
    0.47
    Manifest
    0.47
    courses
    0.46
    climate
    0.45
     আইনে
    0.44
    hemi
    0.44
    addProduct
    0.44
    Bets
    0.44
    Act Density 0.000%

    No Known Activations