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

    Neuronpedia

    INDEX
    Explanations

    correctness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     peoples
    -0.07
     HttpHeaders
    -0.06
    .words
    -0.06
     daddy
    -0.06
    Employee
    -0.06
    /K
    -0.06
     people
    -0.06
     handbook
    -0.06
     famine
    -0.06
    نية
    -0.06
    POSITIVE LOGITS
     Hussein
    0.07
     Comey
    0.07
     reinforce
    0.07
     omin
    0.06
    ederation
    0.06
    Sony
    0.06
     respawn
    0.06
     Colin
    0.06
     Topic
    0.06
    (row
    0.06
    Act Density 0.021%

    No Known Activations