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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sw
    -0.07
    eware
    -0.07
     scrambling
    -0.06
    aim
    -0.06
    ceb
    -0.06
    .middleware
    -0.06
     contempl
    -0.06
    國家
    -0.06
    ih
    -0.06
     Lorem
    -0.06
    POSITIVE LOGITS
    (coords
    0.07
    icontrol
    0.06
     harming
    0.06
    _PLATFORM
    0.06
     Sharma
    0.06
    ρη
    0.06
     cubic
    0.06
    Health
    0.06
     :)
    0.06
    ге
    0.06
    Act Density 0.000%

    No Known Activations