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

    Neuronpedia

    INDEX
    Explanations

    code structure declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    supset
    0.40
     exorc
    0.40
    ignment
    0.39
    eks
    0.38
     sculpture
    0.38
     shrine
    0.38
    vee
    0.38
     skulls
    0.38
    ampur
    0.38
    ৱ
    0.37
    POSITIVE LOGITS
    联盟
    0.42
    തായ
    0.41
    ЕР
    0.39
     OPERATION
    0.39
     möchten
    0.39
     möj
    0.39
    এফ
    0.38
     बलों
    0.38
    OPERATION
    0.38
    Potential
    0.38
    Act Density 0.027%

    No Known Activations