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

    Neuronpedia

    INDEX
    Explanations

    explicit services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Es
    0.48
    hig
    0.48
    the
    0.47
    Ms
    0.47
    Ма
    0.47
    甲
    0.47
     of
    0.46
    味
    0.46
    保護
    0.45
    Des
    0.45
    POSITIVE LOGITS
    н
    0.49
     เป้า
    0.49
     महिले
    0.47
     높아
    0.47
    issense
    0.46
    চ্চার
    0.46
     څخه
    0.45
     prenant
    0.45
     Wolverine
    0.44
     рыба
    0.43
    Act Density 0.000%

    No Known Activations