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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    øl
    -0.08
    erground
    -0.08
    ficas
    -0.08
    listed
    -0.08
    ermann
    -0.08
    adenas
    -0.08
    /general
    -0.08
    Listed
    -0.08
    াদি
    -0.08
    -have
    -0.07
    POSITIVE LOGITS
     Delta
    0.08
     Trabalh
    0.08
     calendário
    0.08
     Kat
    0.07
     किर
    0.07
     incum
    0.07
     sustentabilidade
    0.07
     réserve
    0.07
     weakest
    0.07
     leitor
    0.07
    Act Density 0.003%

    No Known Activations