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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lesbienne
    -0.07
     StObject
    -0.07
     AssemblyCopyright
    -0.07
     دو
    -0.06
     vnitř
    -0.06
     هج
    -0.06
    ุงเทพมหานคร
    -0.06
     butto
    -0.06
     ArrayAdapter
    -0.06
     luxe
    -0.06
    POSITIVE LOGITS
     usually
    0.07
    Shortcut
    0.06
    covery
    0.06
    vi
    0.06
    Filter
    0.06
     Claim
    0.06
    rif
    0.06
    anging
    0.06
     typically
    0.06
    biz
    0.06
    Act Density 0.015%

    No Known Activations