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

    Neuronpedia

    INDEX
    Explanations

    say copyright

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (cn
    -0.07
     coat
    -0.07
    房东
    -0.07
    同学们
    -0.06
    HttpServletRequest
    -0.06
    五千
    -0.06
    世界各国
    -0.06
    AILY
    -0.06
    期内
    -0.06
    cock
    -0.06
    POSITIVE LOGITS
     espacio
    0.07
    大力支持
    0.06
     communities
    0.06
     masa
    0.06
     instancia
    0.06
    _balance
    0.06
     SMP
    0.06
    昝
    0.06
    掖
    0.06
     recommendation
    0.06
    Act Density 0.001%

    No Known Activations