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

    Neuronpedia

    INDEX
    Explanations

    object at rest stays at rest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Acceleration
    0.56
    Gravity
    0.47
     Acceleration
    0.47
     acceleration
    0.46
    acceleration
    0.46
    parseDouble
    0.44
    Athlete
    0.42
    ネット
    0.42
    Deja
    0.41
    Acceler
    0.41
    POSITIVE LOGITS
     inertia
    0.61
     continues
    0.56
     inert
    0.55
     Inert
    0.52
     continuing
    0.52
     inertial
    0.50
     continue
    0.50
     continuar
    0.49
     continuer
    0.49
     shutout
    0.48
    Act Density 0.015%

    No Known Activations