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

    Neuronpedia

    INDEX
    Explanations

    like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     boil
    -0.08
    _scr
    -0.06
    .Validation
    -0.06
    ilitary
    -0.06
    -hours
    -0.06
    usterity
    -0.06
     neh
    -0.06
    oog
    -0.06
    .latitude
    -0.06
     satisfies
    -0.06
    POSITIVE LOGITS
    (username
    0.07
    _graphics
    0.07
     hydraulic
    0.07
    .setViewportView
    0.06
     accidentally
    0.06
     merchandise
    0.06
    .entries
    0.06
    ,event
    0.06
     Edmonton
    0.06
     ack
    0.06
    Act Density 0.006%

    No Known Activations