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

    Neuronpedia

    INDEX
    Explanations

    Specific technical topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Trash
    -0.08
    рма
    -0.07
    tech
    -0.07
    стоя
    -0.07
    _classifier
    -0.06
    蜢
    -0.06
    椪
    -0.06
    _vk
    -0.06
     cyan
    -0.06
    _TITLE
    -0.06
    POSITIVE LOGITS
    .SqlClient
    0.07
     pthread
    0.07
     demise
    0.07
     Rename
    0.07
     불구
    0.07
    .Current
    0.06
    ABCDEFGHIJKLMNOP
    0.06
    sending
    0.06
    พร
    0.06
    &apos
    0.06
    Act Density 0.002%

    No Known Activations