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

    Neuronpedia

    INDEX
    Explanations

    replication

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     večer
    -0.08
     hustle
    -0.07
     Вас
    -0.07
    rieg
    -0.07
     chest
    -0.07
    ño
    -0.07
    oha
    -0.07
     áll
    -0.06
    альном
    -0.06
     Physiology
    -0.06
    POSITIVE LOGITS
     replication
    0.06
    -layout
    0.06
     try
    0.06
    Identifier
    0.06
     Henry
    0.06
    (newUser
    0.06
     gen
    0.06
     Ripple
    0.06
     APS
    0.06
     Square
    0.06
    Act Density 0.002%

    No Known Activations