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

    Neuronpedia

    INDEX
    Explanations

    stage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fell
    -0.07
     profit
    -0.07
    (passport
    -0.07
    非
    -0.07
    债
    -0.07
     money
    -0.06
    _STR
    -0.06
    eea
    -0.06
    weet
    -0.06
     relative
    -0.06
    POSITIVE LOGITS
     stage
    0.20
     Stage
    0.18
     stages
    0.17
    Stage
    0.16
    stage
    0.14
    -stage
    0.13
     staging
    0.11
     stag
    0.10
    _STAGE
    0.10
    .stage
    0.10
    Act Density 0.016%

    No Known Activations