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

    Neuronpedia

    INDEX
    Explanations

    code examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    olian
    -0.08
     motif
    -0.07
     rebel
    -0.07
     dry
    -0.06
     skepticism
    -0.06
    หาก
    -0.06
    701
    -0.06
    /mail
    -0.06
    EMS
    -0.06
     fk
    -0.06
    POSITIVE LOGITS
     serves
    0.07
     jub
    0.06
    ;break
    0.06
    kelig
    0.06
    _keeper
    0.06
    _ne
    0.06
     certifications
    0.06
     JFrame
    0.06
     classifications
    0.06
     втор
    0.06
    Act Density 0.241%

    No Known Activations