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

    Neuronpedia

    INDEX
    Explanations

    code mappings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mert
    0.41
    fords
    0.40
    Spots
    0.38
    Rak
    0.38
    يبقى
    0.37
     grunn
    0.37
    Fle
    0.37
    收益
    0.37
     Meredith
    0.37
     venta
    0.36
    POSITIVE LOGITS
     issue
    0.49
     Issue
    0.44
     jump
    0.42
    issue
    0.42
    thm
    0.41
     मुद्दा
    0.41
     jaw
    0.40
    Issue
    0.38
     argument
    0.38
    াচ্ছে
    0.38
    Act Density 0.001%

    No Known Activations