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

    Neuronpedia

    INDEX
    Explanations

    code delimiting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bactéries
    0.39
    ფორმა
    0.39
     bremsstrahlung
    0.38
     sécrétion
    0.37
    ើញ
    0.37
    ⸩
    0.37
     `=`,
    0.37
     différence
    0.37
     concaten
    0.37
    㣱
    0.37
    POSITIVE LOGITS
    if
    0.55
    //
    0.50
    /*
    0.49
    est
    0.47
    u
    0.46
    ios
    0.46
    ns
    0.43
    /
    0.41
    "
    0.40
    UN
    0.40
    Act Density 0.046%

    No Known Activations