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

    Neuronpedia

    INDEX
    Explanations

    states of matter

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     takie
    0.71
     such
    0.70
     feasts
    0.70
     firearm
    0.69
    グレード
    0.69
     compañeros
    0.67
     แชร์
    0.67
     attendees
    0.67
    abilidades
    0.67
     לע
    0.67
    POSITIVE LOGITS
     Liquids
    0.99
     Due
    0.97
     Chlor
    0.92
     Liquid
    0.91
     Gases
    0.91
     Electrons
    0.90
     Water
    0.89
    Chlor
    0.89
     Gravity
    0.88
     Fluids
    0.88
    Act Density 0.199%

    No Known Activations