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

    Neuronpedia

    INDEX
    Explanations

    Group

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bol
    -0.07
     nob
    -0.06
     profitable
    -0.06
     reconcile
    -0.06
    .rec
    -0.06
    })↵
    -0.06
    орт
    -0.06
    EXTERNAL
    -0.06
    (sigma
    -0.06
    fund
    -0.06
    POSITIVE LOGITS
    �
    0.07
     Important
    0.07
    认
    0.07
    �
    0.07
    equ
    0.06
     tempList
    0.06
    くらい
    0.06
    Wizard
    0.06
     regardless
    0.06
     considered
    0.06
    Act Density 0.010%

    No Known Activations