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

    Neuronpedia

    INDEX
    Explanations

    Social networks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )+'
    -0.07
     ENTITY
    -0.07
    stats
    -0.07
    (loc
    -0.06
     createdAt
    -0.06
    imagin
    -0.06
    _exp
    -0.06
    Spread
    -0.06
     Smartphone
    -0.06
    FirstChild
    -0.06
    POSITIVE LOGITS
     والد
    0.07
    以为
    0.07
    ，而且
    0.07
     nem
    0.06
    哭
    0.06
    uctions
    0.06
    ichage
    0.06
     Guardians
    0.06
    rink
    0.06
    者的
    0.06
    Act Density 0.032%

    No Known Activations