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

    Neuronpedia

    INDEX
    Explanations

    Apache

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    。これ
    -0.07
    _SCRIPT
    -0.07
    λλ
    -0.06
    ların
    -0.06
    ;;
    -0.06
         
    -0.06
    λ
    -0.06
    .findall
    -0.06
    _models
    -0.06
     Cum
    -0.06
    POSITIVE LOGITS
     Apache
    0.11
    Apache
    0.11
     apache
    0.10
    apache
    0.08
     ange
    0.07
    あり
    0.07
     azure
    0.07
    expert
    0.06
     moh
    0.06
    Tap
    0.06
    Act Density 0.005%

    No Known Activations