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

    Neuronpedia

    INDEX
    Explanations

    input questions for answers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oops
    0.44
     deck
    0.41
     سر
    0.41
     úspě
    0.39
    主に
    0.39
    SALE
    0.38
     बेचने
    0.37
    滩
    0.36
     заниматься
    0.36
     veterin
    0.36
    POSITIVE LOGITS
    arity
    0.41
     sensores
    0.40
    abeled
    0.38
    传感
    0.38
    urrent
    0.37
     맞는
    0.37
    渇
    0.37
    ismiss
    0.37
    triggers
    0.37
    insulated
    0.37
    Act Density 0.001%

    No Known Activations