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

    Neuronpedia

    INDEX
    Explanations

    code and documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     podob
    -0.07
    应
    -0.07
    Services
    -0.06
     mieux
    -0.06
    FontAwesomeIcon
    -0.06
    免
    -0.06
     hardcoded
    -0.06
     quadr
    -0.06
     Maui
    -0.06
     Engineers
    -0.06
    POSITIVE LOGITS
    .requests
    0.07
    pad
    0.07
     Garten
    0.07
     Japon
    0.06
     فیلم
    0.06
    DOWN
    0.06
    stock
    0.06
    avra
    0.06
     clientele
    0.06
    κού
    0.06
    Act Density 0.237%

    No Known Activations