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

    Neuronpedia

    INDEX
    Explanations

    web development code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     קר
    -0.07
    的那一
    -0.07
     따
    -0.07
     BSD
    -0.07
    𝕖
    -0.06
     ]];
    -0.06
    >@
    -0.06
    �
    -0.06
    .rmi
    -0.06
    .LatLng
    -0.06
    POSITIVE LOGITS
     input
    0.07
    address
    0.07
    forgettable
    0.07
    Collections
    0.07
    missible
    0.07
     addict
    0.07
     employing
    0.07
    广泛的
    0.07
     Output
    0.06
     Exhibition
    0.06
    Act Density 0.108%

    No Known Activations