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

    Neuronpedia

    INDEX
    Explanations

    especially not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Doug
    0.47
    Religion
    0.47
    Gy
    0.44
    Burning
    0.44
     prévention
    0.43
    ཋ
    0.43
    ὃ
    0.43
     Doug
    0.42
    드는
    0.42
    Douglas
    0.42
    POSITIVE LOGITS
    ação
    0.50
     até
    0.47
     quanto
    0.46
     ponad
    0.45
     junto
    0.45
     encontro
    0.45
     üzerinden
    0.44
     añ
    0.43
     conm
    0.43
     dönd
    0.43
    Act Density 0.001%

    No Known Activations