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

    Neuronpedia

    INDEX
    Explanations

    status

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (note
    -0.07
     unlike
    -0.07
    分钟
    -0.07
     depressive
    -0.07
     Romania
    -0.06
     دانشگاه
    -0.06
    Describe
    -0.06
    影響
    -0.06
     attackers
    -0.06
    _loop
    -0.06
    POSITIVE LOGITS
     prestige
    0.07
     status
    0.07
     outsiders
    0.07
     nguy
    0.07
    нося
    0.07
     достав
    0.06
     extortion
    0.06
     berhasil
    0.06
     Score
    0.06
     Fest
    0.06
    Act Density 0.009%

    No Known Activations