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

    Neuronpedia

    INDEX
    Explanations

    programming / environment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Do
    0.45
     গন
    0.40
     Otros
    0.38
     Reli
    0.38
     millón
    0.38
     Fest
    0.37
     자신
    0.37
     Lo
    0.37
     ril
    0.36
     Oo
    0.36
    POSITIVE LOGITS
    pairwise
    0.46
    軐
    0.40
    ShaderProgram
    0.40
    шли
    0.39
    сії
    0.39
     пол
    0.39
    hy
    0.38
    shape
    0.38
    괌
    0.38
     প্রতিযোগ
    0.38
    Act Density 0.001%

    No Known Activations