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

    Neuronpedia

    INDEX
    Explanations

    technical jargon and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jedes
    0.46
    ＆
    0.45
     tred
    0.39
     რამდ
    0.39
    やお
    0.37
     and
    0.37
     metų
    0.37
     cnt
    0.37
    crafted
    0.36
     meats
    0.36
    POSITIVE LOGITS
     neoclassical
    0.45
     arguably
    0.42
     unquestion
    0.40
     Radiological
    0.39
     hypothetical
    0.38
     proverbial
    0.38
     Implications
    0.38
    ুখী
    0.38
     axiomatic
    0.37
    oretically
    0.37
    Act Density 0.000%

    No Known Activations