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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     infographic
    -0.07
     NSObject
    -0.07
    -standard
    -0.07
    ρου
    -0.07
    eriod
    -0.06
    BMI
    -0.06
     glu
    -0.06
     fists
    -0.06
     setw
    -0.06
     Titanic
    -0.06
    POSITIVE LOGITS
     DNS
    0.06
    alcon
    0.06
     internally
    0.06
     accomplished
    0.06
    ็อต
    0.06
     Jag
    0.06
     отказ
    0.06
    ior
    0.06
     REPRESENT
    0.06
    instances
    0.06
    Act Density 0.002%

    No Known Activations