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

    Neuronpedia

    INDEX
    Explanations

    Action/Instruction words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     добав
    -0.07
     glowing
    -0.07
    анная
    -0.07
    호
    -0.07
    -and
    -0.07
    ующие
    -0.07
    ，却
    -0.07
    iệp
    -0.06
    .feedback
    -0.06
    しゃ
    -0.06
    POSITIVE LOGITS
     Refriger
    0.07
    -work
    0.07
     refriger
    0.07
    Remove
    0.07
     Tunisia
    0.07
     Reserve
    0.06
    .enter
    0.06
     lay
    0.06
     Translator
    0.06
     Init
    0.06
    Act Density 0.222%

    No Known Activations