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

    Neuronpedia

    INDEX
    Explanations

    metadata

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _identifier
    -0.07
     गर
    -0.07
    .COMP
    -0.06
     робити
    -0.06
     sandwiches
    -0.06
    .Cons
    -0.06
     Е
    -0.06
     spun
    -0.06
    mes
    -0.06
    わけ
    -0.06
    POSITIVE LOGITS
     crackdown
    0.08
    ailand
    0.07
    Traits
    0.07
     dragon
    0.07
    ingroup
    0.07
    070
    0.07
     or
    0.06
     농
    0.06
    692
    0.06
    abet
    0.06
    Act Density 0.000%

    No Known Activations