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

    Neuronpedia

    INDEX
    Explanations

    judicial credibility

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    退回
    -0.07
    adapt
    -0.07
    udas
    -0.07
    -0.07
     år
    -0.07
     Weed
    -0.06
     ×
    -0.06
    תוס
    -0.06
     Sug
    -0.06
     Kore
    -0.06
    POSITIVE LOGITS
    出现
    0.07
     hemorrh
    0.07
    (Channel
    0.07
    還是
    0.07
    準
    0.06
     mastering
    0.06
     Sour
    0.06
    _r
    0.06
    ռ
    0.06
    Speech
    0.06
    Act Density 0.003%

    No Known Activations