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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hall
    -0.08
     Vocabulary
    -0.07
    cest
    -0.07
     Assess
    -0.07
     LOOP
    -0.07
     av
    -0.07
     Arab
    -0.07
    宁愿
    -0.07
    .linear
    -0.07
     Canal
    -0.07
    POSITIVE LOGITS
     בריא
    0.07
    多く
    0.07
    Shortly
    0.07
     국내
    0.07
     souha
    0.07
     empresas
    0.07
     home
    0.06
    疏导
    0.06
    jam
    0.06
    method
    0.06
    Act Density 0.010%

    No Known Activations