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

    Neuronpedia

    INDEX
    Explanations

    RAN or ran

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    argeon
    0.36
     statunit
    0.34
     ocurr
    0.34
    gere
    0.33
    Recent
    0.33
    0.33
    chenko
    0.33
    вершена
    0.33
    gow
    0.33
    rakt
    0.33
    POSITIVE LOGITS
    धीर
    0.50
    ದಲು
    0.44
    न्या
    0.41
    데요
    0.40
     ран
    0.39
    ്‍
    0.38
    imals
    0.38
    ική
    0.38
    RAN
    0.38
     rans
    0.38
    Act Density 0.010%

    No Known Activations