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

    Neuronpedia

    INDEX
    Explanations

    gluons, quarks, protons, neutrons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     जन्
    0.47
     kelahiran
    0.46
     لديك
    0.44
    犾
    0.43
     阅读
    0.41
    沬
    0.41
    湋
    0.41
     intrauterine
    0.40
    жают
    0.40
     McClure
    0.39
    POSITIVE LOGITS
    ASS
    0.42
    ỹ
    0.40
    Def
    0.40
     AC
    0.39
    AS
    0.38
    Pr
    0.38
    AC
    0.38
     TYPE
    0.38
    conv
    0.37
    ens
    0.37
    Act Density 0.000%

    No Known Activations