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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    察
    -0.07
     Houses
    -0.07
     Corona
    -0.06
     submitting
    -0.06
     cerco
    -0.06
     sanitized
    -0.06
     '-',
    -0.06
     Human
    -0.06
    wf
    -0.06
     tapes
    -0.06
    POSITIVE LOGITS
     έχει
    0.07
    Continue
    0.07
     smaller
    0.07
     ASUS
    0.06
     delet
    0.06
     شکل
    0.06
    ۱۳
    0.06
     preprocessing
    0.06
     smoother
    0.06
     Eigen
    0.06
    Act Density 0.000%

    No Known Activations