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

    Neuronpedia

    INDEX
    Explanations

    state and transitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     loan
    0.49
     poppies
    0.48
    ثر
    0.48
    fish
    0.46
    atual
    0.46
     mailing
    0.46
     mortar
    0.46
    loan
    0.46
     ಗ್ರಾ
    0.46
    fishing
    0.45
    POSITIVE LOGITS
     Transitions
    0.57
     Transition
    0.56
     transitions
    0.54
     transition
    0.53
    Transitions
    0.53
     Synchron
    0.52
    State
    0.50
     Tracks
    0.49
     currentState
    0.49
    Synchron
    0.48
    Act Density 0.023%

    No Known Activations