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

    Neuronpedia

    INDEX
    Explanations

    space and code explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     userAnswer
    0.40
     અલ
    0.39
     son
    0.38
    见过
    0.38
     "¿
    0.37
    ሢ
    0.36
    ामान्य
    0.36
     ав
    0.35
     산업
    0.35
     Omaha
    0.35
    POSITIVE LOGITS
    ্সর
    0.50
    EDEN
    0.45
     espacio
    0.39
    EP
    0.37
     Footage
    0.36
    iddhi
    0.36
    espa
    0.36
    Ky
    0.36
    ECC
    0.35
    Space
    0.35
    Act Density 0.000%

    No Known Activations