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

    Neuronpedia

    INDEX
    Explanations

    Hello, World!

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ،
    0.41
     ("[
    0.40
    "",
    0.38
    "،
    0.38
    ("
    0.38
    がない
    0.37
    matical
    0.37
     Просто
    0.36
    ნიშვნ
    0.36
    確實
    0.36
    POSITIVE LOGITS
    s
    0.50
     illetve
    0.47
    n
    0.45
     с
    0.44
     což
    0.42
    aka
    0.42
     اتارنا
    0.42
     mutta
    0.40
    ands
    0.40
     który
    0.40
    Act Density 0.044%

    No Known Activations