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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     detect
    -0.07
    053
    -0.06
     our
    -0.06
    Tue
    -0.06
    void
    -0.06
     separate
    -0.06
     Grace
    -0.06
    49
    -0.06
     Loài
    -0.06
     Ack
    -0.06
    POSITIVE LOGITS
     عل
    0.08
     रहन
    0.07
     --↵↵
    0.07
    기를
    0.06
    ứt
    0.06
    سان
    0.06
    →→
    0.06
    ічний
    0.06
    이를
    0.06
     �
    0.06
    Act Density 0.090%

    No Known Activations