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

    Neuronpedia

    INDEX
    Explanations

    code and language analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     сна
    -0.08
     бед
    -0.08
     PureComponent
    -0.08
    amer
    -0.07
    ships
    -0.07
    Gun
    -0.07
     boots
    -0.06
    _visit
    -0.06
     lust
    -0.06
    sten
    -0.06
    POSITIVE LOGITS
    -ph
    0.06
     karşılaş
    0.06
     잡
    0.06
     tout
    0.06
    _ord
    0.06
    _greater
    0.06
    consult
    0.06
     ngăn
    0.06
     Avec
    0.06
    Specify
    0.06
    Act Density 0.091%

    No Known Activations