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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stop
    -0.07
     gói
    -0.07
    Expect
    -0.07
     Radius
    -0.07
     "",
    -0.07
     अग
    -0.07
     ostensibly
    -0.06
    琴
    -0.06
    _Delete
    -0.06
    	X
    -0.06
    POSITIVE LOGITS
     fright
    0.07
    ㅋㅋㅋㅋ
    0.06
    ていた
    0.06
    alloca
    0.06
    Political
    0.06
     Committee
    0.06
    committee
    0.06
    ))))↵↵
    0.06
    .FromSeconds
    0.06
    غير
    0.06
    Act Density 0.007%

    No Known Activations