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

    Neuronpedia

    INDEX
    Explanations

    Cross Science

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TestSuite
    0.38
     gourmet
    0.37
    ingale
    0.37
     hexadecimal
    0.36
     ash
    0.36
     constitutional
    0.36
    ault
    0.35
    ormais
    0.35
    嗥
    0.35
     Cours
    0.34
    POSITIVE LOGITS
    Cross
    0.62
    Science
    0.61
     Cross
    0.61
     Science
    0.57
     cross
    0.56
    CCC
    0.56
    cross
    0.56
     CCC
    0.55
    CROSS
    0.52
    科學
    0.52
    Act Density 0.001%

    No Known Activations