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

    Neuronpedia

    INDEX
    Explanations

    scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     سن
    -0.08
     Delaware
    -0.07
    ække
    -0.07
     suck
    -0.07
    Henry
    -0.07
     Oregon
    -0.07
     Terra
    -0.07
    wget
    -0.06
     Fuck
    -0.06
     Shore
    -0.06
    POSITIVE LOGITS
     demonstration
    0.06
    Cluster
    0.06
     ga
    0.06
    意见
    0.06
    ꧈
    0.06
    (si
    0.06
     finalize
    0.06
    县政府
    0.06
    ();
↵
↵
    0.06
    (layout
    0.06
    Act Density 0.004%

    No Known Activations