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

    Neuronpedia

    INDEX
    Explanations

    affinity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ordeal
    -0.07
     レ
    -0.07
    _preds
    -0.07
     cows
    -0.07
    �
    -0.07
     expl
    -0.07
     december
    -0.07
    杨
    -0.07
    para
    -0.06
    Que
    -0.06
    POSITIVE LOGITS
    "/>
    0.06
     affinity
    0.06
     Refer
    0.06
     expresses
    0.06
    ]
↵
    0.06
    ];
    0.06
    /ref
    0.06
    ermint
    0.06
     antigen
    0.06
     《
    0.06
    Act Density 0.003%

    No Known Activations