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

    Neuronpedia

    INDEX
    Explanations

    shapes and weaving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    님의
    -0.07
    .roles
    -0.06
     classy
    -0.06
    _secure
    -0.06
     rs
    -0.06
     表
    -0.06
     virt
    -0.06
     trai
    -0.06
    DirectoryName
    -0.06
     Game
    -0.06
    POSITIVE LOGITS
     deployments
    0.07
    _REL
    0.07
    PIC
    0.06
     Momentum
    0.06
    dart
    0.06
    dney
    0.06
     olursa
    0.06
    abee
    0.06
     tink
    0.06
    oz
    0.06
    Act Density 0.331%

    No Known Activations