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

    Neuronpedia

    INDEX
    Explanations

    Policy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stále
    -0.06
     Š
    -0.06
     kèo
    -0.06
     zoekt
    -0.06
    しの
    -0.06
    .executeUpdate
    -0.06
     준
    -0.06
     subprocess
    -0.06
    сен
    -0.06
    /base
    -0.06
    POSITIVE LOGITS
     oc
    0.07
    قت
    0.07
    ppo
    0.07
     rast
    0.06
    ￣￣￣￣
    0.06
    azi
    0.06
    =-
    0.06
     jLabel
    0.06
    _ALLOC
    0.06
     sails
    0.06
    Act Density 0.000%

    No Known Activations