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

    Neuronpedia

    INDEX
    Explanations

    actions and steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     सब्सिडी
    0.81
     sistemi
    0.77
    িয়েছেন
    0.76
     Sistemi
    0.74
     بواسطة
    0.73
     varietà
    0.72
     FULLER
    0.72
     半
    0.70
     rohkem
    0.70
    elfalt
    0.69
    POSITIVE LOGITS
     actions
    1.68
     action
    1.63
     Actions
    1.54
    Action
    1.50
     acciones
    1.50
     Action
    1.50
     steps
    1.49
    action
    1.46
    Actions
    1.40
    actions
    1.39
    Act Density 0.818%

    No Known Activations