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

    Neuronpedia

    INDEX
    Explanations

    code/documentation fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AnchorStyles
    -0.46
    StoryboardSegue
    -0.42
     Zacks
    -0.41
    хьтан
    -0.40
     defaultstate
    -0.40
    rophi
    -0.40
     AssemblyTitle
    -0.39
    Chham
    -0.39
     Akismet
    -0.38
    差し
    -0.38
    POSITIVE LOGITS
    `,
    0.69
    mbggenerated
    0.64
    Хьажоргаш
    0.61
     ]
    0.60
    addCriterion
    0.60
    깐
    0.59
     Italijanski
    0.59
    новниш
    0.59
    `).
    0.58
    .},
    0.57
    Act Density 0.008%

    No Known Activations