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

    Neuronpedia

    INDEX
    Explanations

    free

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     atomic
    -0.07
     cryptographic
    -0.07
     monot
    -0.07
    .controllers
    -0.07
     loyal
    -0.07
     stationary
    -0.06
    .bean
    -0.06
    -sum
    -0.06
     algebra
    -0.06
     traditional
    -0.06
    POSITIVE LOGITS
     رابطه
    0.06
    (per
    0.06
    .relationship
    0.06
     Session
    0.06
     hlad
    0.06
     及
    0.06
     Lance
    0.06
     đình
    0.06
    ὰ
    0.06
    orta
    0.06
    Act Density 0.011%

    No Known Activations