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
     humano
    -0.07
     uphe
    -0.07
    ください
    -0.07
     UV
    -0.06
    观
    -0.06
     méth
    -0.06
    缩
    -0.06
     дека
    -0.06
    (prev
    -0.06
     vå
    -0.06
    POSITIVE LOGITS
    phia
    0.07
    fa
    0.06
    department
    0.06
    ()?.
    0.06
    .group
    0.06
    �i
    0.06
    rypto
    0.06
    itime
    0.06
    formData
    0.06
     objectives
    0.06
    Act Density 0.051%

    No Known Activations