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

    Neuronpedia

    INDEX
    Explanations

    code structure, parameters, file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     codebase
    0.39
    ृता
    0.36
    安慰
    0.36
    otherapie
    0.36
    INDOW
    0.34
     wikipagina
    0.34
     takže
    0.34
    ципа
    0.34
    ليل
    0.33
     distanc
    0.33
    POSITIVE LOGITS
    ="
    0.42
    ?=
    0.41
    などの
    0.40
     ஆகியவை
    0.39
     ஆகிய
    0.39
    ?
    0.38
     महिला
    0.38
    ":
    0.38
     등의
    0.37
    基本
    0.37
    Act Density 0.055%

    No Known Activations