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

    Neuronpedia

    INDEX
    Explanations

    copy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stepped
    -0.08
    Act
    -0.07
     Blick
    -0.07
     Blend
    -0.07
     rg
    -0.07
    rike
    -0.07
    备份
    -0.07
    os
    -0.06
    .af
    -0.06
     és
    -0.06
    POSITIVE LOGITS
    .':
    0.06
     +**************
    0.06
    Unsupported
    0.06
     ча
    0.06
    ?)↵
    0.06
    민주
    0.06
    [][]
    0.06
    ofstream
    0.06
    航空
    0.06
     KeyboardInterrupt
    0.06
    Act Density 0.002%

    No Known Activations