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

    Neuronpedia

    INDEX
    Explanations

    high value / excellence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    renderer
    0.54
     الي
    0.54
    兩
    0.52
    ٨
    0.51
    funciones
    0.50
    Renderer
    0.48
    resultados
    0.48
    比利
    0.48
     Го
    0.48
    func
    0.47
    POSITIVE LOGITS
     rapp
    0.52
     calving
    0.51
    tch
    0.50
    gård
    0.50
    dde
    0.50
     cercle
    0.49
     hutan
    0.49
     Coconut
    0.49
    मर्रा
    0.48
    ක්
    0.48
    Act Density 0.000%

    No Known Activations