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

    Neuronpedia

    INDEX
    Explanations

    mermaid code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    жнарод
    0.46
     dzie
    0.45
    iophorus
    0.45
    Ꮟ
    0.43
     aplatis
    0.42
    mprj
    0.42
    Bracketing
    0.42
     جوړونکي
    0.41
    ꪽ
    0.41
    URNING
    0.41
    POSITIVE LOGITS
     {
    0.49
     "
    0.44
    aire
    0.42
    ();
    0.42
    da
    0.41
    {
    0.41
    ()
    0.40
    dd
    0.39
    I
    0.39
    (
    0.39
    Act Density 0.002%

    No Known Activations