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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Secret
    -0.07
     airl
    -0.07
    訚
    -0.07
     Anthem
    -0.07
    .math
    -0.06
    医护
    -0.06
    核心技术
    -0.06
    isel
    -0.06
     domaine
    -0.06
    各个环节
    -0.06
    POSITIVE LOGITS
     unequiv
    0.07
     chromosomes
    0.07
    قا
    0.07
    ‾
    0.07
     Chain
    0.07
     ,,
    0.07
     hoe
    0.07
     prognosis
    0.06
    0.06
     additive
    0.06
    Act Density 0.001%

    No Known Activations