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

    Neuronpedia

    INDEX
    Explanations

    game attributes and skills

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Introductory
    -0.82
    зумі
    -0.78
    Archi
    -0.78
     水晶
    -0.76
    messungen
    -0.75
     زی
    -0.74
    tapete
    -0.73
    Nec
    -0.72
     imma
    -0.71
    getNew
    -0.71
    POSITIVE LOGITS
     attribute
    1.13
     attributes
    0.88
    Recovery
    0.85
     RECOVERY
    0.84
     guard
    0.84
     Recovery
    0.82
    属性
    0.79
     Skills
    0.78
    attribute
    0.77
     Skill
    0.77
    Act Density 0.009%

    No Known Activations