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

    Neuronpedia

    INDEX
    Explanations

    editorial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Agent
    -0.07
    compact
    -0.06
     stressful
    -0.06
    (number
    -0.06
     Owl
    -0.06
     ناحیه
    -0.06
     hvor
    -0.06
    ounds
    -0.06
     perpendicular
    -0.06
    =>
    -0.06
    POSITIVE LOGITS
     editorial
    0.28
     Editorial
    0.19
    说话
    0.07
     initialState
    0.07
     advisory
    0.07
     время
    0.06
    .Marshal
    0.06
     addObserver
    0.06
     redhead
    0.06
     resolution
    0.06
    Act Density 0.002%

    No Known Activations