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

    Neuronpedia

    INDEX
    Explanations

    doubt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _scenario
    -0.07
     telesc
    -0.07
    _Node
    -0.07
    _invoke
    -0.07
     Interfaces
    -0.07
     capacidad
    -0.06
    (pages
    -0.06
    ível
    -0.06
     navigation
    -0.06
     mosquito
    -0.06
    POSITIVE LOGITS
     doubt
    0.17
     doubts
    0.13
     doubted
    0.12
     Doub
    0.11
     doub
    0.11
     doubtful
    0.10
     дру
    0.08
     Low
    0.07
     Rift
    0.07
     Cubs
    0.07
    Act Density 0.006%

    No Known Activations