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

    Neuronpedia

    INDEX
    Explanations

    time mentions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    志
    -0.07
    ados
    -0.07
    tasks
    -0.06
    LU
    -0.06
     Excellence
    -0.06
    肌
    -0.06
    dued
    -0.06
    _ll
    -0.06
    ं
    -0.06
     Great
    -0.06
    POSITIVE LOGITS
    ώσεις
    0.07
    ])),↵
    0.07
     Matt
    0.07
     cyst
    0.06
     CBS
    0.06
     Dems
    0.06
    Fullscreen
    0.06
    ('-',
    0.06
     akan
    0.06
     ακό
    0.06
    Act Density 0.117%

    No Known Activations