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

    Neuronpedia

    INDEX
    Explanations

    extend

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ultan
    -0.07
     commented
    -0.06
    Sol
    -0.06
    应
    -0.06
     estimates
    -0.06
    SD
    -0.06
     thinks
    -0.06
    Option
    -0.06
     proper
    -0.06
    _Is
    -0.06
    POSITIVE LOGITS
    .sn
    0.07
     dignity
    0.07
    /tr
    0.06
     numpy
    0.06
    ษ
    0.06
     خانو
    0.06
    вор
    0.06
    γέν
    0.06
     Moines
    0.06
    ůr
    0.06
    Act Density 0.005%

    No Known Activations