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

    Neuronpedia

    INDEX
    Explanations

    limitations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     المش
    -0.07
     beetle
    -0.07
    Separ
    -0.06
     Damien
    -0.06
     inhibition
    -0.06
    _tokenize
    -0.06
     menu
    -0.06
     latch
    -0.06
     architectural
    -0.06
     unf
    -0.06
    POSITIVE LOGITS
     ทอง
    0.07
    rer
    0.06
    Years
    0.06
    워크
    0.06
     Kr
    0.06
    ffi
    0.06
     Comics
    0.06
     IntPtr
    0.06
    Capability
    0.06
    lič
    0.06
    Act Density 0.001%

    No Known Activations