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

    Neuronpedia

    INDEX
    Explanations

    line

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    roots
    -0.07
     librarian
    -0.07
    .
↵
↵
    -0.07
    .getElements
    -0.07
    client
    -0.06
    .");↵↵
    -0.06
    .";
    -0.06
    фра
    -0.06
    npj
    -0.06
     CLL
    -0.06
    POSITIVE LOGITS
     Absolute
    0.06
    hong
    0.06
     только
    0.06
    rium
    0.06
     adequate
    0.06
     οικο
    0.06
     stable
    0.06
     Pets
    0.06
    -range
    0.06
     sorumlu
    0.06
    Act Density 0.093%

    No Known Activations