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

    Neuronpedia

    INDEX
    Explanations

    Names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     awesome
    -0.07
     loan
    -0.07
    Woman
    -0.07
     parses
    -0.06
     chairs
    -0.06
     inputs
    -0.06
    egers
    -0.06
    Criteria
    -0.06
     SwiftUI
    -0.06
     Virt
    -0.06
    POSITIVE LOGITS
    сол
    0.06
     teaser
    0.06
     Vince
    0.06
    ━
    0.06
     선택
    0.06
     임
    0.06
     affecting
    0.06
     linked
    0.06
    _opcode
    0.06
    악
    0.06
    Act Density 0.005%

    No Known Activations