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

    Neuronpedia

    INDEX
    Explanations

    bullet points and emphasis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    0.46
    ud
    0.45
     Smart
    0.45
    с
    0.44
    ê
    0.42
     Crisis
    0.41
    ק
    0.41
    ang
    0.40
    ège
    0.39
    ong
    0.39
    POSITIVE LOGITS
    <u>
    0.46
    underline
    0.42
    (!)
    0.41
    MONTH
    0.39
     appunto
    0.39
    STRING
    0.38
     くれ
    0.38
     vutta
    0.38
    ښت
    0.38
    ScriptAssemblies
    0.38
    Act Density 0.060%

    No Known Activations