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

    Neuronpedia

    INDEX
    Explanations

    Multi-lingual social media prompts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    дается
    -0.08
    Total
    -0.08
    就是说
    -0.08
     fermé
    -0.08
     caracter
    -0.08
     characterization
    -0.08
    {\
    -0.08
    Average
    -0.08
    Characteristics
    -0.07
     depressive
    -0.07
    POSITIVE LOGITS
     �
    0.15
    精彩
    0.13
    ✨
    0.13
     beautifully
    0.13
     великолеп
    0.13
     �
    0.12
     शानदार
    0.12
     bustling
    0.12
     sizzling
    0.12
     effortlessly
    0.12
    Act Density 0.262%

    No Known Activations