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

    Neuronpedia

    INDEX
    Explanations

    code documentation parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ب
    0.56
    ون
    0.52
    وان
    0.49
    ру
    0.49
    alse
    0.48
    ou
    0.47
    ellos
    0.46
    ap
    0.46
    och
    0.46
    ólico
    0.45
    POSITIVE LOGITS
     t
    0.51
    <0xD0>
    0.49
     synthesis
    0.48
     k
    0.48
     this
    0.46
     bundle
    0.46
     by
    0.46
     default
    0.46
     isa
    0.45
     visible
    0.45
    Act Density 0.049%

    No Known Activations