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

    Neuronpedia

    INDEX
    Explanations

    code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ópez
    0.23
     pecado
    0.23
     susceptibles
    0.22
     thiab
    0.22
    stethoscope
    0.22
     physicochemical
    0.21
     ప్రస్తు
    0.21
    你就
    0.21
    0.21
    ുകയും
    0.21
    POSITIVE LOGITS
    った
    0.31
    ة
    0.29
    Demo
    0.27
    Example
    0.25
    ー
    0.25
    ing
    0.24
    ToServer
    0.24
    er
    0.24
    Exists
    0.24
    ovanje
    0.24
    Act Density 0.302%

    No Known Activations