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

    Neuronpedia

    INDEX
    Explanations

    a mix of programming code, abbreviations, legal/medical terminology, and uncommon words

    oai_token-act-pair · gemini-2.0-flash

    AC

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.71
     Tacitus
    -0.56
     Theſe
    -0.55
    FunctionFlags
    -0.54
     Jefus
    -0.53
     nargin
    -0.52
     tanam
    -0.52
    neum
    -0.51
    </thead>
    -0.51
     becauſe
    -0.50
    POSITIVE LOGITS
     protoimpl
    0.57
    tagHelperRunner
    0.55
    "]];
    0.55
    Hochspringen
    0.52
    unknownFields
    0.51
     Carried
    0.50
    fond
    0.49
    webElementXpaths
    0.49
    ToAction
    0.48
     carried
    0.48
    Act Density 6.108%

    No Known Activations