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

    Neuronpedia

    INDEX
    Explanations

    support

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    鬘
    -0.08
     Featured
    -0.07
    蕻
    -0.07
    前所
    -0.07
    epy
    -0.07
    โพ
    -0.07
    メッ
    -0.07
    很容易
    -0.07
    urst
    -0.06
    嵴
    -0.06
    POSITIVE LOGITS
    (opt
    0.08
    _security
    0.07
    עביר
    0.07
     situação
    0.07
    亦
    0.07
     promote
    0.07
     Dũng
    0.07
    -----↵
    0.07
     louis
    0.07
     sentencing
    0.07
    Act Density 0.009%

    No Known Activations