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

    Neuronpedia

    INDEX
    Explanations

    Punctuation/code characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ographic
    -0.07
     architecture
    -0.07
     automatic
    -0.07
     Bayesian
    -0.07
    tics
    -0.07
     Pipe
    -0.07
    Metrics
    -0.06
     Physics
    -0.06
     engines
    -0.06
    istics
    -0.06
    POSITIVE LOGITS
     sní
    0.07
     flesh
    0.07
    καν
    0.06
     Meng
    0.06
     Camden
    0.06
     EXTI
    0.06
     майбут
    0.06
    �
    0.06
    ΥΝ
    0.06
    675
    0.06
    Act Density 0.027%

    No Known Activations