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

    Neuronpedia

    INDEX
    Explanations

    recommend

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    눈
    -0.08
     polic
    -0.08
    NO
    -0.07
     minutes
    -0.07
     BUT
    -0.07
     Bluetooth
    -0.07
     modest
    -0.07
    MIN
    -0.07
     eril
    -0.07
     배
    -0.07
    POSITIVE LOGITS
     empfohlen
    0.10
     advisable
    0.09
    推荐
    0.09
     empfehlen
    0.09
     recomendable
    0.09
     recomendado
    0.09
     Recommended
    0.08
     advised
    0.08
     рекомендуется
    0.08
     כיום
    0.08
    Act Density 0.045%

    No Known Activations