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

    Neuronpedia

    INDEX
    Explanations

    abilities, powers, and stats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MOQ
    0.45
     CRIMINAL
    0.44
    mathb
    0.43
     засе
    0.42
    竣工
    0.42
    DataAnnotations
    0.42
    riminal
    0.42
    imai
    0.42
     BOARDSIZE
    0.42
    criminals
    0.41
    POSITIVE LOGITS
     teleport
    1.00
     healing
    0.97
     ability
    0.91
    Healing
    0.91
     heal
    0.89
     Healing
    0.89
     healer
    0.86
     invisibility
    0.82
    Tele
    0.81
     Tele
    0.80
    Act Density 0.074%

    No Known Activations