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

    Neuronpedia

    INDEX
    Explanations

    cylinder

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    opol
    -0.07
    лений
    -0.07
    ětí
    -0.06
     undesirable
    -0.06
     Emmanuel
    -0.06
     chained
    -0.06
    odal
    -0.06
    El
    -0.06
    -model
    -0.06
    ивать
    -0.06
    POSITIVE LOGITS
    stops
    0.07
     createAction
    0.06
     Deadline
    0.06
     regained
    0.06
    	restore
    0.06
    icolon
    0.06
     csr
    0.06
    キャ
    0.06
    cerer
    0.06
    (utf
    0.06
    Act Density 0.053%

    No Known Activations