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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assistant
    -0.07
    pwd
    -0.07
    Finished
    -0.07
    Cri
    -0.06
    .Member
    -0.06
    .list
    -0.06
     economical
    -0.06
     switching
    -0.06
    	util
    -0.06
     湖
    -0.06
    POSITIVE LOGITS
     XXX
    0.07
    _img
    0.06
    'd
    0.06
    _PROTO
    0.06
    ’d
    0.06
    ATIONS
    0.06
    }*/↵↵
    0.06
    ])));↵
    0.06
     Exercises
    0.06
    ()]);↵
    0.06
    Act Density 0.003%

    No Known Activations