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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ribbon
    -0.07
    Attributes
    -0.06
    .rows
    -0.06
     exotic
    -0.06
     towels
    -0.06
     representatives
    -0.06
    Sat
    -0.06
     door
    -0.06
    apache
    -0.06
     invoke
    -0.06
    POSITIVE LOGITS
    ells
    0.07
    σή
    0.07
    lardan
    0.07
    -wsj
    0.07
     المنطقة
    0.06
    โ
    0.06
     گر
    0.06
    .Package
    0.06
    .Timer
    0.06
    éro
    0.06
    Act Density 0.047%

    No Known Activations