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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .bool
    -0.07
     inverse
    -0.07
    inverse
    -0.06
    monthly
    -0.06
    itrust
    -0.06
    attach
    -0.06
     enters
    -0.06
    .cn
    -0.06
    .Destroy
    -0.06
    -rays
    -0.06
    POSITIVE LOGITS
     juices
    0.06
    anches
    0.06
     cestu
    0.06
     مرد
    0.06
     hosting
    0.06
    Е
    0.06
    ůj
    0.06
     ăn
    0.06
     ness
    0.06
    	player
    0.06
    Act Density 0.040%

    No Known Activations