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

    Neuronpedia

    INDEX
    Explanations

    angles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hitting
    -0.09
     మూడు
    -0.08
    Null
    -0.08
     సర
    -0.08
    _initialize
    -0.08
     трех
    -0.07
    Analyze
    -0.07
    -three
    -0.07
    ńczy
    -0.07
    Cmd
    -0.07
    POSITIVE LOGITS
     المض
    0.08
     poses
    0.08
     неприят
    0.08
     cipher
    0.08
     କ
    0.08
     advers
    0.08
     kapag
    0.08
     uneven
    0.08
     સતત
    0.07
     Supplier
    0.07
    Act Density 0.014%

    No Known Activations