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

    Neuronpedia

    INDEX
    Explanations

    holding, room, feeling, only, db

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ∪
    0.42
    ∩
    0.40
    NK
    0.40
    НЫ
    0.38
    eroom
    0.38
    ทรง
    0.37
    ökk
    0.36
     Samu
    0.35
     GUIContent
    0.35
    kappa
    0.34
    POSITIVE LOGITS
     एस्ट्र
    0.41
     disediakan
    0.39
     eyewitness
    0.38
     performed
    0.37
     available
    0.37
     솔
    0.36
    potion
    0.36
    ಿದ್ದೇನೆ
    0.36
    Ret
    0.36
    Leg
    0.36
    Act Density 0.000%

    No Known Activations