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

    Neuronpedia

    INDEX
    Explanations

    *>

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kort
    -0.07
    ocese
    -0.06
     TH
    -0.06
    ()));↵↵
    -0.06
     لك
    -0.06
    очь
    -0.06
     }};↵
    -0.06
     slots
    -0.06
     ignorance
    -0.05
     🙂↵↵
    -0.05
    POSITIVE LOGITS
    عل
    0.07
    grav
    0.07
     cocoa
    0.07
    ppo
    0.07
    ісля
    0.06
    690
    0.06
     prescriptions
    0.06
     Uttar
    0.06
     hast
    0.06
     Mothers
    0.06
    Act Density 0.002%

    No Known Activations