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

    Neuronpedia

    INDEX
    Explanations

    Goal, Agent, Materials, Symptoms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     batches
    0.48
     loans
    0.47
     lots
    0.46
     appointment
    0.46
     things
    0.44
     beberapa
    0.43
     WITHIN
    0.43
     appointments
    0.42
     to
    0.42
     Exhibits
    0.42
    POSITIVE LOGITS
    aguchi
    0.50
    ribe
    0.47
     capitaine
    0.47
    ри
    0.47
     periód
    0.46
    órc
    0.46
    zględ
    0.45
    desIP
    0.45
    ରି
    0.44
    ೇಳ
    0.44
    Act Density 0.005%

    No Known Activations