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

    Neuronpedia

    INDEX
    Explanations

    degree and magnitude

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Saheb
    0.35
     thisTrack
    0.33
     théorème
    0.32
     Luật
    0.32
     getUsersBy
    0.31
     〢
    0.31
     résoudre
    0.30
     gérer
    0.30
     będ
    0.30
    效应
    0.30
    POSITIVE LOGITS
    est
    0.39
    ened
    0.39
    ish
    0.38
    -
    0.38
     levels
    0.38
    ,
    0.37
    ely
    0.34
     large
    0.34
     type
    0.34
     enough
    0.34
    Act Density 0.525%

    No Known Activations