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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     occurrence
    -0.07
     VAT
    -0.06
    Nano
    -0.06
     canal
    -0.06
     Apt
    -0.06
     Standard
    -0.06
    十六
    -0.05
    reements
    -0.05
    SCALE
    -0.05
     başlam
    -0.05
    POSITIVE LOGITS
    ійської
    0.08
     Aug
    0.07
     exh
    0.07
    чук
    0.07
    -column
    0.06
    (use
    0.06
    -hit
    0.06
    ction
    0.06
     enchanted
    0.06
    ................................
    0.06
    Act Density 0.004%

    No Known Activations