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

    Neuronpedia

    INDEX
    Explanations

    technical system components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    J
    -1.32
     beschlossen
    -1.23
     połą
    -1.10
    P
    -1.08
    K
    -1.05
    D
    -1.04
    &
    -0.99
     D
    -0.97
    O
    -0.96
     Z
    -0.96
    POSITIVE LOGITS
     rigide
    1.42
     stadion
    1.37
     pittores
    1.27
     Humanos
    1.24
     majest
    1.23
    "';
    1.23
     visuel
    1.23
     konfigura
    1.23
     alfab
    1.21
    alı
    1.20
    Act Density 0.293%

    No Known Activations