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

    Neuronpedia

    INDEX
    Explanations

    all

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -fire
    -0.08
    顔
    -0.08
     entertained
    -0.08
     உள்ளிட்ட
    -0.08
     ਹਾਂ
    -0.08
    (mail
    -0.08
    -global
    -0.08
     inbox
    -0.08
     fornecedores
    -0.08
     procur
    -0.08
    POSITIVE LOGITS
     perfek
    0.07
     aparent
    0.07
     relativ
    0.07
     Carroll
    0.07
     Martín
    0.07
     Ese
    0.07
    yam
    0.07
     yab
    0.07
     self
    0.07
     parag
    0.07
    Act Density 0.001%

    No Known Activations