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

    Neuronpedia

    INDEX
    Explanations

    cover

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ạnh
    -0.07
     Payload
    -0.07
    _CSR
    -0.07
    .userAgent
    -0.06
    cctor
    -0.06
    eil
    -0.06
    cus
    -0.06
    Metadata
    -0.06
    該
    -0.06
    lığının
    -0.06
    POSITIVE LOGITS
    Unity
    0.07
    ..........
    0.07
    OSH
    0.06
    IONS
    0.06
    人民共和国
    0.06
    -ended
    0.06
     HUGE
    0.06
     mins
    0.06
    471
    0.06
     stunned
    0.06
    Act Density 0.013%

    No Known Activations