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

    Neuronpedia

    INDEX
    Explanations

    access

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Med
    -0.07
     Med
    -0.06
     Anniversary
    -0.06
    ant
    -0.06
     U
    -0.06
    مج
    -0.06
    Netflix
    -0.06
    cur
    -0.06
    .ReadLine
    -0.06
    احی
    -0.06
    POSITIVE LOGITS
     noct
    0.07
     можете
    0.07
     아직
    0.06
    即
    0.06
     phức
    0.06
     ensuring
    0.06
     extracting
    0.06
    bsites
    0.06
     menstr
    0.06
     unfinished
    0.06
    Act Density 0.020%

    No Known Activations