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

    Neuronpedia

    INDEX
    Explanations

    having

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    یدی
    -0.07
     lender
    -0.06
     тру
    -0.06
    .minecraft
    -0.06
    ازي
    -0.06
     Isl
    -0.06
     draft
    -0.06
    Flight
    -0.06
     Diploma
    -0.06
     thậm
    -0.06
    POSITIVE LOGITS
     interess
    0.07
    boa
    0.06
     heures
    0.06
    noDB
    0.06
     conocer
    0.06
    .success
    0.06
     згод
    0.06
     Praze
    0.06
     Truy
    0.06
     retir
    0.06
    Act Density 0.203%

    No Known Activations