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

    Neuronpedia

    INDEX
    Explanations

    URLs to online resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ferrugineux
    0.20
     মাংস
    0.19
    ☟
    0.19
     Erklärung
    0.18
    നങ്ങൾ
    0.18
     propriétés
    0.18
     scald
    0.18
    朊
    0.18
     parametrization
    0.17
    🦵
    0.17
    POSITIVE LOGITS
    6
    0.34
    4
    0.32
    1
    0.32
    3
    0.31
    8
    0.30
    7
    0.30
    2
    0.30
    9
    0.29
    5
    0.28
    0
    0.22
    Act Density 0.306%

    No Known Activations