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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .getItem
    -0.09
    饕
    -0.08
    ;left
    -0.08
     bartender
    -0.08
     safeguards
    -0.07
    停电
    -0.07
    텝
    -0.07
    开车
    -0.07
    胜
    -0.07
    igator
    -0.07
    POSITIVE LOGITS
     Delta
    0.08
     altered
    0.07
    	sig
    0.07
     |
↵
    0.06
    ==
    0.06
    以致
    0.06
     alter
    0.06
     ואח
    0.06
    -Ch
    0.06
     licensee
    0.06
    Act Density 0.034%

    No Known Activations