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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    аду
    -0.07
    ertiary
    -0.06
    -0.06
     Criteria
    -0.06
    SPAN
    -0.06
    .vec
    -0.05
    -0.05
     Comparative
    -0.05
    ону
    -0.05
    .vertices
    -0.05
    POSITIVE LOGITS
    steam
    0.07
     const
    0.07
     hend
    0.07
    Steam
    0.06
     necesario
    0.06
     jan
    0.06
     ripping
    0.06
     isIn
    0.06
     Ahmed
    0.06
     Params
    0.06
    Act Density 0.015%

    No Known Activations