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

    Neuronpedia

    INDEX
    Explanations

    col

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sam
    -0.07
    styles
    -0.07
     KM
    -0.07
    .FileReader
    -0.06
     diffuse
    -0.06
     Nir
    -0.06
     작은
    -0.06
     Plan
    -0.06
    getY
    -0.06
    uger
    -0.06
    POSITIVE LOGITS
    чила
    0.06
     sklad
    0.06
    �력
    0.06
    _PHASE
    0.06
    Saved
    0.06
     NET
    0.06
     Gab
    0.05
    �
    0.05
     вариан
    0.05
     лі
    0.05
    Act Density 0.001%

    No Known Activations