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

    Neuronpedia

    INDEX
    Explanations

    Instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aos
    -0.07
     Agu
    -0.06
     cp
    -0.06
     Ub
    -0.06
     acl
    -0.06
    เคย
    -0.06
    .Execution
    -0.06
    avorites
    -0.06
     Dra
    -0.06
    idle
    -0.06
    POSITIVE LOGITS
    SCRIPT
    0.07
     yaptığı
    0.06
    pes
    0.06
    /big
    0.06
     Post
    0.06
    /misc
    0.06
     iş
    0.06
    矢
    0.06
    /pass
    0.06
    ünchen
    0.06
    Act Density 0.065%

    No Known Activations