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

    Neuronpedia

    INDEX
    Explanations

    SKOS, rdfs, labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PIP
    0.40
     bouch
    0.39
    湃
    0.38
    heder
    0.37
    ESSITY
    0.37
    Caller
    0.37
    FileInfo
    0.37
     eukaryotes
    0.37
    Quadrant
    0.37
    Eloquent
    0.36
    POSITIVE LOGITS
     SK
    0.41
    न्हें
    0.40
     ToolsVersion
    0.37
     jus
    0.35
     outweighed
    0.35
     juggle
    0.35
    '];?>
    0.34
    NORE
    0.34
    textbackslash
    0.34
    ⠛
    0.34
    Act Density 0.001%

    No Known Activations