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

    Neuronpedia

    INDEX
    Explanations

    academic papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .shutdown
    -0.07
    vice
    -0.07
    ∣
    -0.07
     situations
    -0.07
    💇
    -0.07
    üz
    -0.07
    ув
    -0.07
    عني
    -0.07
     Verizon
    -0.07
    tearDown
    -0.07
    POSITIVE LOGITS
    很大
    0.07
    潦
    0.07
     Freed
    0.07
     hayatını
    0.07
    鸟成长记
    0.07
    黟
    0.06
     Doub
    0.06
     Cary
    0.06
    ении
    0.06
    ざ
    0.06
    Act Density 0.424%

    No Known Activations