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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .links
    -0.07
    stand
    -0.06
     Jane
    -0.06
     Tuple
    -0.06
    Fu
    -0.06
    TEM
    -0.06
     XX
    -0.06
     ramifications
    -0.06
     cambio
    -0.06
     transformer
    -0.06
    POSITIVE LOGITS
    inceton
    0.06
    cir
    0.06
     evenings
    0.06
     excitement
    0.06
     foll
    0.06
     توجه
    0.06
    恩
    0.06
     Aviation
    0.06
     kể
    0.06
     lucr
    0.06
    Act Density 0.000%

    No Known Activations