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

    Neuronpedia

    INDEX
    Explanations

    Excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     benefici
    -0.09
     motto
    -0.07
     muz
    -0.07
    世
    -0.07
     idea
    -0.07
     brand
    -0.07
     Bottom
    -0.07
     pretext
    -0.07
     लक
    -0.06
     ADC
    -0.06
    POSITIVE LOGITS
    正确
    0.07
     Darren
    0.06
    .vehicle
    0.06
    _ulong
    0.06
     Rivera
    0.06
    ěl
    0.06
    _normals
    0.06
    .INVISIBLE
    0.06
    ốn
    0.06
    .Space
    0.06
    Act Density 0.000%

    No Known Activations