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

    Neuronpedia

    INDEX
    Explanations

    code-related elements typically associated with defining actions in test frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    import or start of turn followed by classifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WireFormatLite
    -0.47
     coroa
    -0.45
    LabelTagHelper
    -0.43
     cielos
    -0.43
     cumbre
    -0.43
    expandindo
    -0.43
     asamblea
    -0.42
     muñeca
    -0.41
    Билгалдахарш
    -0.40
     spolup
    -0.40
    POSITIVE LOGITS
    mybatisplus
    0.71
    baomidou
    0.64
     AssemblyCompany
    0.55
     Opa
    0.52
     NIP
    0.52
     Outback
    0.51
     inters
    0.50
    Incon
    0.50
     spi
    0.49
     Bic
    0.49
    Act Density 0.000%

    No Known Activations