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

    Neuronpedia

    INDEX
    Explanations

    attack

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    嘘
    -0.09
     dévelop
    -0.08
    .resp
    -0.07
    司令
    -0.07
    	↵	↵
    -0.07
     ]
    -0.07
    Boom
    -0.06
    ध
    -0.06
    Stop
    -0.06
    平方米
    -0.06
    POSITIVE LOGITS
    _prim
    0.08
     سي
    0.07
    overall
    0.07
    phi
    0.07
    /utility
    0.07
     ri
    0.07
    III
    0.07
     tslib
    0.07
    เขา
    0.06
    zo
    0.06
    Act Density 0.017%

    No Known Activations