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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     greedy
    -0.09
     careless
    -0.08
     ironic
    -0.08
     mediocre
    -0.08
    ;++
    -0.08
     attackers
    -0.08
     solitaire
    -0.08
     impossible
    -0.08
     sarcas
    -0.08
     sarcast
    -0.07
    POSITIVE LOGITS
     공동
    0.11
     gezamen
    0.11
     agreed
    0.11
     Joint
    0.11
     jointly
    0.10
    Joint
    0.10
     harmon
    0.10
     gemeinsamen
    0.10
     gezamenlijk
    0.10
    双方
    0.10
    Act Density 0.043%

    No Known Activations