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

    Neuronpedia

    INDEX
    Explanations

    why

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    σου
    -0.07
    _ctxt
    -0.07
     faaliyet
    -0.06
    _continuous
    -0.06
    μου
    -0.06
    иск
    -0.06
     plaats
    -0.06
    _slot
    -0.06
     carbohydrate
    -0.06
     conversation
    -0.06
    POSITIVE LOGITS
    0.07
    さんは
    0.07
    ,.
    0.06
    Carrier
    0.06
     ElseIf
    0.06
     Doctor
    0.06
     Osc
    0.06
     =>
↵
    0.06
    =Math
    0.06
    opcode
    0.06
    Act Density 0.023%

    No Known Activations