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

    Neuronpedia

    INDEX
    Explanations

    not just

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inferiores
    0.52
     pravil
    0.46
     facil
    0.45
     abund
    0.45
     scala
    0.44
     scare
    0.44
     обнаружи
    0.42
    受け
    0.41
     ниже
    0.41
     feces
    0.41
    POSITIVE LOGITS
    pN
    0.48
    CoO
    0.45
    ({},
    0.45
    Known
    0.42
    arguments
    0.42
    ]));
    0.42
    ethics
    0.42
    cabin
    0.42
    Whole
    0.41
    Buildings
    0.41
    Act Density 0.000%

    No Known Activations