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

    Neuronpedia

    INDEX
    Explanations

    need for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     efficace
    0.56
     concentrates
    0.52
     overwhel
    0.50
    ,_-
    0.48
     convuls
    0.48
     efficiently
    0.47
     invigorating
    0.47
     beetles
    0.46
    PAAm
    0.46
     hsize
    0.46
    POSITIVE LOGITS
    ↵
    0.50
    奬
    0.49
     Rend
    0.48
    Wrapping
    0.46
    console
    0.46
    Promise
    0.44
    畬
    0.43
     vidare
    0.43
    ipsis
    0.42
    }
    0.42
    Act Density 0.000%

    No Known Activations