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

    Neuronpedia

    INDEX
    Explanations

    virtues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _OPENGL
    -0.07
    literal
    -0.06
    _HERSHEY
    -0.06
     mango
    -0.06
     zaměstn
    -0.06
    ofilm
    -0.06
     italiana
    -0.06
    -budget
    -0.06
     italiane
    -0.06
     Achie
    -0.06
    POSITIVE LOGITS
    Goods
    0.08
     drawbacks
    0.06
    .Lib
    0.06
    .guard
    0.06
    -fed
    0.06
    .LogInformation
    0.06
     resourceName
    0.06
     noreferrer
    0.06
    icie
    0.06
     başlam
    0.06
    Act Density 0.132%

    No Known Activations