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

    Neuronpedia

    INDEX
    Explanations

    differentiated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    że
    -0.07
    内容
    -0.07
    ssize
    -0.06
    樓
    -0.06
    创
    -0.06
     reach
    -0.06
    FACE
    -0.06
    .za
    -0.06
    Gb
    -0.06
    Urls
    -0.06
    POSITIVE LOGITS
     гр
    0.07
     pokoj
    0.07
     Sag
    0.06
     insisted
    0.06
     irresist
    0.06
    κλη
    0.06
     accepted
    0.06
     goodwill
    0.06
    unicorn
    0.06
     appellant
    0.06
    Act Density 0.001%

    No Known Activations