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

    Neuronpedia

    INDEX
    Explanations

    program states and current values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     devs
    0.29
     community
    0.29
     callbacks
    0.29
     holidays
    0.28
     dup
    0.28
     Undo
    0.28
     boosts
    0.28
     AL
    0.27
     id
    0.27
     trillions
    0.27
    POSITIVE LOGITS
    ClFN
    0.32
    URNIZOR
    0.29
    шым
    0.29
    Weber
    0.29
    нер
    0.29
    BERGER
    0.28
     perfused
    0.28
    睪
    0.28
    вле
    0.27
    Scanning
    0.27
    Act Density 0.010%

    No Known Activations