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

    Neuronpedia

    INDEX
    Explanations

    Medical classifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    анти
    -0.07
    niest
    -0.06
     technician
    -0.06
     roaring
    -0.06
    Insurance
    -0.06
    Computer
    -0.06
    azar
    -0.06
    _scaling
    -0.06
    ombat
    -0.06
    illery
    -0.06
    POSITIVE LOGITS
    .callbacks
    0.07
     numero
    0.07
     цел
    0.07
    .Invalid
    0.07
     Libert
    0.07
     verschied
    0.06
     Burg
    0.06
    ,re
    0.06
     Wave
    0.06
    Thrown
    0.06
    Act Density 0.031%

    No Known Activations