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

    Neuronpedia

    INDEX
    Explanations

    beet

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     أبو
    -0.07
    ίος
    -0.06
     perg
    -0.06
    uş
    -0.06
     forts
    -0.06
     copyright
    -0.06
    ancellable
    -0.06
    UTERS
    -0.06
    olucion
    -0.06
    üsseldorf
    -0.06
    POSITIVE LOGITS
     updateTime
    0.07
     Tough
    0.07
     التق
    0.07
    _files
    0.07
     대행
    0.07
    Increase
    0.06
    도를
    0.06
    _sms
    0.06
    >User
    0.06
     Modes
    0.06
    Act Density 0.001%

    No Known Activations