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

    Neuronpedia

    INDEX
    Explanations

    полож

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mountains
    -0.07
    .getZ
    -0.07
    <>();↵↵
    -0.06
     Wars
    -0.06
     Forums
    -0.06
     premiered
    -0.06
     timp
    -0.06
    ElementException
    -0.06
    /name
    -0.06
    _match
    -0.06
    POSITIVE LOGITS
     полож
    0.13
     Vladim
    0.07
    opcode
    0.07
     البر
    0.07
    .reward
    0.06
    ilage
    0.06
     lying
    0.06
    _overlay
    0.06
    _config
    0.06
    ,email
    0.06
    Act Density 0.001%

    No Known Activations