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

    Neuronpedia

    INDEX
    Explanations

    Generalizing actions of a few

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fija
    -0.09
    aben
    -0.08
     ventaja
    -0.08
    legenheit
    -0.08
     گی
    -0.07
    Una
    -0.07
    omod
    -0.07
     Root
    -0.07
     Parliamentary
    -0.07
     usability
    -0.07
    POSITIVE LOGITS
     extremists
    0.10
    '];
↵
    0.09
     terceiros
    0.09
     extremist
    0.09
    '])->
    0.09
    '];
↵
↵
    0.08
     individus
    0.08
    ']?>"
    0.08
    ']);
    0.08
     mauvais
    0.08
    Act Density 0.067%

    No Known Activations