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

    Neuronpedia

    INDEX
    Explanations

    machine learning frameworks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    edi
    -0.08
    }`)↵
    -0.08
    Mining
    -0.08
    Halloween
    -0.07
     defeating
    -0.07
    (issue
    -0.07
    Deviation
    -0.07
    Quotation
    -0.07
     TRE
    -0.07
     punctuation
    -0.07
    POSITIVE LOGITS
    卷
    0.08
     glorious
    0.07
     собственного
    0.07
     girl
    0.07
     glor
    0.07
    /simple
    0.07
     Unite
    0.07
     włas
    0.07
     cooperación
    0.07
    arse
    0.07
    Act Density 0.001%

    No Known Activations