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

    Neuronpedia

    INDEX
    Explanations

    javascript

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     offences
    -0.07
     arena
    -0.07
    —at
    -0.07
    Dependency
    -0.07
    UBE
    -0.06
    ati
    -0.06
     учеб
    -0.06
    ampionship
    -0.06
     amis
    -0.06
    すす
    -0.06
    POSITIVE LOGITS
     �
    0.07
     adore
    0.07
    Quest
    0.06
    _te
    0.06
    ूच
    0.06
     ******************************************************************************/↵↵
    0.06
    ้ท
    0.06
     krit
    0.06
     تخصص
    0.06
    leitung
    0.06
    Act Density 0.001%

    No Known Activations