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

    Neuronpedia

    INDEX
    Explanations

    computer code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    预览
    -0.07
    peating
    -0.06
    yms
    -0.06
    ิท
    -0.06
     VALID
    -0.06
     irony
    -0.06
    chio
    -0.06
    ğini
    -0.06
     【
    -0.06
    iydi
    -0.06
    POSITIVE LOGITS
     kö
    0.07
     nr
    0.07
     espec
    0.07
    银
    0.06
     necess
    0.06
     اینتر
    0.06
     sınır
    0.06
    .ff
    0.06
     notas
    0.06
     Sheridan
    0.06
    Act Density 0.000%

    No Known Activations