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

    Neuronpedia

    INDEX
    Explanations

    deal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     前
    -0.07
    _scripts
    -0.07
     öz
    -0.07
    Ģ
    -0.07
     Spr
    -0.07
    <thead
    -0.07
     ErrorMessage
    -0.06
     ADD
    -0.06
     để
    -0.06
    被
    -0.06
    POSITIVE LOGITS
     weaknesses
    0.07
    .validation
    0.07
     Deal
    0.07
     gcc
    0.06
     deals
    0.06
     най
    0.06
    .Authorization
    0.06
     tendency
    0.06
    -country
    0.06
    aler
    0.06
    Act Density 0.004%

    No Known Activations