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

    Neuronpedia

    INDEX
    Explanations

    methodology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     liver
    -0.08
     burns
    -0.07
     parts
    -0.07
     coats
    -0.07
    'en
    -0.07
     reaction
    -0.07
     reactions
    -0.07
     fart
    -0.06
     pets
    -0.06
     side
    -0.06
    POSITIVE LOGITS
    onomy
    0.07
     Mandela
    0.06
    /png
    0.06
     MLA
    0.06
    视频
    0.06
     Agenda
    0.06
    >tag
    0.06
    indic
    0.06
    Lex
    0.06
     проблем
    0.06
    Act Density 0.029%

    No Known Activations