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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions or code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    А
    1.24
    де
    1.05
    াতি
    1.05
     सफाया
    1.02
     roam
    0.99
     extin
    0.98
     Fiverr
    0.98
     acup
    0.98
    Α
    0.96
     continua
    0.95
    POSITIVE LOGITS
    й
    1.52
    ש
    1.48
    которы
    1.16
    of
    1.13
    ist
    1.10
    which
    1.09
    ark
    1.09
    id
    1.07
    iet
    1.07
    providers
    1.05
    Act Density 0.047%

    No Known Activations