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

    Neuronpedia

    INDEX
    Explanations

    Hamiltonian paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     азарт
    -0.09
    ībā
    -0.08
     marche
    -0.08
     liked
    -0.08
     올
    -0.08
    こ
    -0.08
     ///
    -0.07
     ?>"
    -0.07
     соль
    -0.07
     olvid
    -0.07
    POSITIVE LOGITS
     Públic
    0.08
     principi
    0.08
     Mobility
    0.08
     donor
    0.08
     Constituição
    0.08
    _Block
    0.08
     Conditioning
    0.07
    -dist
    0.07
     regiões
    0.07
     Brandenburg
    0.07
    Act Density 0.007%

    No Known Activations