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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cheryl
    -0.07
     +(
    -0.06
    swap
    -0.06
     catapult
    -0.06
    cing
    -0.06
    调整
    -0.06
    验证
    -0.06
    Tasks
    -0.06
    interp
    -0.06
    Derived
    -0.06
    POSITIVE LOGITS
     BOOLEAN
    0.08
     MASTER
    0.07
    ILLE
    0.06
     locks
    0.06
     Prairie
    0.06
    -bound
    0.06
    ινη
    0.06
    _EDGE
    0.06
     Glass
    0.06
    .Offset
    0.06
    Act Density 0.046%

    No Known Activations