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

    Neuronpedia

    INDEX
    Explanations

    language and text generation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sweets
    -0.07
    Angular
    -0.06
    кой
    -0.06
     giorni
    -0.06
     widow
    -0.06
     RCMP
    -0.06
    ()>
    -0.06
     serious
    -0.06
     threatening
    -0.06
    idade
    -0.05
    POSITIVE LOGITS
     меропри
    0.07
     BU
    0.07
    (field
    0.07
    .drawString
    0.06
    ้ด
    0.06
    alore
    0.06
    alg
    0.06
    hhh
    0.06
    inston
    0.06
     sır
    0.06
    Act Density 0.039%

    No Known Activations