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

    Neuronpedia

    INDEX
    Explanations

    seem

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sensitive
    -0.07
     marché
    -0.07
    ;"
    -0.07
    ٪
    -0.07
    арч
    -0.06
    957
    -0.06
    (global
    -0.06
     менее
    -0.06
    ...",
    -0.06
    705
    -0.06
    POSITIVE LOGITS
    電
    0.07
     tug
    0.07
     開
    0.07
     paste
    0.06
    /perl
    0.06
     dinosaur
    0.06
    ่าย
    0.06
     inaugur
    0.06
    Burn
    0.06
    ppe
    0.06
    Act Density 0.025%

    No Known Activations