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

    Neuronpedia

    INDEX
    Explanations

    GUI elements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    にて
    -0.07
    れど
    -0.07
    .unsplash
    -0.07
    就是
    -0.07
    Today
    -0.07
     matt
    -0.07
     Univers
    -0.06
    medium
    -0.06
     могу
    -0.06
    oolStrip
    -0.06
    POSITIVE LOGITS
    XT
    0.06
     coolant
    0.06
     canonical
    0.06
     configur
    0.06
    ritten
    0.06
     NK
    0.06
     fermented
    0.06
    igner
    0.06
     BK
    0.06
     robotic
    0.06
    Act Density 0.029%

    No Known Activations