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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    âte
    -0.07
     sketch
    -0.07
     REUTERS
    -0.07
     Anniversary
    -0.07
     anticipation
    -0.06
    search
    -0.06
    ulation
    -0.06
     sal
    -0.06
     smith
    -0.06
    astr
    -0.06
    POSITIVE LOGITS
     따
    0.07
     cid
    0.07
     discret
    0.06
     deferred
    0.06
    rather
    0.06
     dine
    0.06
     coquine
    0.06
    geber
    0.06
    모
    0.06
     PGA
    0.06
    Act Density 0.011%

    No Known Activations