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

    Neuronpedia

    INDEX
    Explanations

    javascript canvas properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uberculosis
    0.30
    «.
    0.28
     moléculas
    0.28
     jednej
    0.28
    ».
    0.28
     मनुष्य
    0.27
     metabolismo
    0.27
    URNIZOR
    0.27
     вопро
    0.27
    ourtney
    0.27
    POSITIVE LOGITS
     (
    0.32
     reverses
    0.27
     ರ
    0.27
     mini
    0.27
     देखील
    0.27
     （
    0.26
     కూడా
    0.26
     UAE
    0.25
    (
    0.25
     تاکہ
    0.25
    Act Density 0.601%

    No Known Activations