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

    Neuronpedia

    INDEX
    Explanations

    London and Thames

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    響
    -0.07
    =batch
    -0.07
    堆
    -0.07
     undecided
    -0.06
    (endpoint
    -0.06
     fetching
    -0.06
     Window
    -0.06
    _question
    -0.06
     trường
    -0.06
     esse
    -0.06
    POSITIVE LOGITS
    PrimaryKey
    0.07
    Monthly
    0.06
    fol
    0.06
    DataSource
    0.06
    visor
    0.06
     Перв
    0.06
    PerPixel
    0.06
    -dominated
    0.06
    _excel
    0.06
    unsqueeze
    0.06
    Act Density 0.009%

    No Known Activations