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

    Neuronpedia

    INDEX
    Explanations

    adding dates and data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dihydro
    0.36
    ెంబ
    0.34
     нередко
    0.34
    件事情
    0.33
    }$.
    0.31
    स्तिष्क
    0.30
    êne
    0.30
    EQU
    0.30
    非常的
    0.30
    ке
    0.29
    POSITIVE LOGITS
     manually
    0.49
     here
    0.48
     this
    0.46
    0
    0.45
     only
    0.44
     below
    0.44
     aqui
    0.44
     +
    0.43
     +=
    0.43
     approx
    0.43
    Act Density 1.057%

    No Known Activations