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

    Neuronpedia

    INDEX
    Explanations

    JSON structure and code elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mga
    0.39
     isang
    0.39
     konkrét
    0.37
    많은
    0.37
     específicamente
    0.37
     zahlreiche
    0.36
     kanilang
    0.36
    también
    0.36
     berbagai
    0.35
     erity
    0.35
    POSITIVE LOGITS
    _
    0.73
    _'
    0.54
    _[
    0.52
    _(
    0.51
    ()
    0.50
    _${
    0.48
    ەکە
    0.47
    _{
    0.47
    ttes
    0.47
    "_
    0.47
    Act Density 0.365%

    No Known Activations