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

    Neuronpedia

    INDEX
    Explanations

    _EXPORT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Belmont
    -0.07
    anı
    -0.07
     museums
    -0.06
     Karlov
    -0.06
    �
    -0.06
    Mappings
    -0.06
     vulnerabilities
    -0.06
    orting
    -0.06
    船
    -0.06
    τικό
    -0.06
    POSITIVE LOGITS
    _EXPORT
    0.07
     "-",
    0.07
     составляет
    0.06
    reas
    0.06
     ساعت
    0.06
     obchod
    0.06
    템
    0.06
     gadgets
    0.06
     دارم
    0.06
    abi
    0.06
    Act Density 0.001%

    No Known Activations