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

    Neuronpedia

    INDEX
    Explanations

    code/system-related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    裘
    -0.08
     ceux
    -0.07
    ໃ
    -0.07
    ועל
    -0.07
     costume
    -0.07
     jeunes
    -0.07
    ilet
    -0.07
     poids
    -0.07
    uits
    -0.07
     vieux
    -0.07
    POSITIVE LOGITS
    (object
    0.07
    响应
    0.07
    	System
    0.07
    ilestone
    0.07
     ")";↵
    0.07
    三方
    0.07
    _phrase
    0.07
    OLE
    0.07
    <option
    0.06
    历史
    0.06
    Act Density 0.010%

    No Known Activations