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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Initial
    -0.07
     continuation
    -0.06
     woodland
    -0.06
    herence
    -0.06
     recovering
    -0.06
    arrival
    -0.06
     jm
    -0.06
    .Manager
    -0.06
    废
    -0.06
     Jays
    -0.06
    POSITIVE LOGITS
     fools
    0.07
    flamm
    0.06
    ["_
    0.06
    Marks
    0.06
    μο
    0.06
    ighter
    0.06
    ภาษ
    0.06
     uuid
    0.06
    َة
    0.06
    "x
    0.06
    Act Density 0.052%

    No Known Activations