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

    Neuronpedia

    INDEX
    Explanations

    card game strategy hands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kiosk
    0.54
     Hakone
    0.47
     kiosks
    0.45
     सबके
    0.43
    蜒
    0.41
     Spartan
    0.41
    肝
    0.41
    Jed
    0.40
    髂
    0.40
     स्तर
    0.39
    POSITIVE LOGITS
     bluff
    0.63
     situational
    0.52
     ambiguous
    0.48
     positional
    0.47
     polarization
    0.47
     steals
    0.46
     opponent
    0.45
     ambigu
    0.45
     renverse
    0.45
     baits
    0.45
    Act Density 0.005%

    No Known Activations